Stock price prediction is a crucial task in financial market analysis due to its impact on investment decision-making. This study aims to apply the Gated Recurrent Unit (GRU) model to forecast the stock price of ANTM.JK using historical time series data. A total of 12 experimental models were developed by varying data split ratios, window sizes, epochs, and batch sizes to identify the optimal model configuration. Model performance was evaluated using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). The results show that the GRU model is capable of predicting stock prices with high accuracy, achieving an accuracy of 98.02%. The RMSE values ranged from 57.78 to 91.09, MAE values ranged from 38.20 to 62.87, and MAPE values ranged from 1.98% to 3.22%. The best-performing model was Model 7, with a 70:30 training–testing split, a window size of 30, 50 epochs, and a batch size of 16, which produced the lowest error values among all models. These findings indicate that GRU is an effective and reliable approach for modeling nonlinear and dynamic stock price time series and has strong potential for supporting financial market analysis and investment decision-making.
A major earthquake struck Lombok, West Nusa Tenggara, in 2018, causing significant infrastructure damage, including in North Lombok Regency. This study aims to analyze land cover changes in North Lombok Regency before and after the earthquake using Sentinel-2 Level-1C satellite imagery. Through supervised classification using the Maximum Likelihood method, changes in the area of various land cover types, such as Bare Land, Paddy Field, Dense Vegetation, Water Bodies, and Built-up Areas, were identified and analyzed temporally in 2017, 2020, and 2023. The results show that the earthquake caused drastic changes in land cover in the study area, particularly a decrease in the area of dense vegetation and an increase in the area of bare land. These changes indicate significant ecosystem disruption caused by the earthquake. Subsequently, a recovery trend was observed in the 2020-2023 period. Changes in land cover, especially in built-up areas and bare land, are consistent with the earthquake's impact and subsequent reconstruction efforts.
A graph 𝐺 is defined as a finite nonempty set 𝑉 of objects called vertices (vertex for singular) together with a possibly empty set of 𝐸 ⊆ {{𝑢, 𝑣} ∣ 𝑢, 𝑣 ∈ 𝑉} called edges. One of interesting topic in graph theory is graph labelling. Super edge magic total labeling is a special form of total edge magic labeling, where vertex labels must come from the set {1,2,…,|𝑉|}, while edge labels come from the remainder of the set {1,2,…,|𝑉|+|𝐸|}. Formally, this labeling is a bijective mapping: 𝑓 : 𝑉 ∪ 𝐸→{1,2,…,|𝑉|+|𝐸|} with the following conditions: 𝑓(𝑣) ∈ {1,2,...,|𝑉|} ∀𝑣 ∈ 𝑉 where there is a constant number 𝑘 such that for every edge 𝑒 = 𝑢𝑣 ∈ 𝐸, 𝑓(𝑢) + 𝑓(𝑒) + 𝑓(𝑣) = 𝑘. The main focus of this research is to determine the existence and construction of super edge-magic total labeling on cartesian product graph 𝐶𝑚 × 𝑃𝑛 with additional pendants. In this study, we get that 𝐶𝑚 × 𝑃𝑛 with pendants are graphs with super edge-magic total labelling’s by constructing the labeling of their vertices and edges, thereby obtaining a magic constant 𝑘.
Cryptocurrency is one of the digital assets that is increasingly popular for investment in Indonesia. However, the price movements of cryptocurrencies tend to be volatile, as prices can change at any time and are not easy to predict. This study aims to predict cryptocurrency price movements using the Long Short-Term Memory Algorithm (LSTM) and Moving Average Convergence Divergence (MACD). LSTM is an algorithm used to generate optimal weights and biases in modeling cryptocurrency data, while MACD is used to analyze trends and momentum in cryptocurrency prices. The data used consists of daily closing prices of Bitcoin (BTC), totaling 809 data points. The data is divided into 70% (566 data) for the training process and 30% (243 data) for the testing process. From this data, patterns are formed with five inputs and one output, resulting in 561 patterns for the training process and 238 patterns for the testing process. The LSTM and MACD processes for predicting cryptocurrency include procedures for data input, data division, parameter initialization, LSTM calculation, average error evaluation, and MACD calculation. Based on the program implementation, with several parameter values, the average error difference obtained during the training stage is 0.0695 and 0.0303 during the testing stage. Because the average error difference obtained is relatively small, this indicates that LSTM-MACD is capable of recognizing data patterns and predicting data effectively.
Nilpotent elements in modular rings play a fundamental role in understanding the algebraic structure of rings and their applications in various mathematical domains. Motivated by the need to explore the interplay between algebraic and combinatorial representations, this study introduces and investigates nilpotent graphs constructed from rings of integers modulo prime powers. We begin by characterizing nilpotent sets and establishing theorems that describe their distribution and algebraic behavior. Using these characterizations, we construct nilpotent graphs, where vertices represent nilpotent elements and edges reflect their interactions. The structural properties of these graphs are examined, and several well known topological indices, such as the Zagreb, Harary, Hyper Wiener, Randić, Harmonic, Sombor, and Schultz indices, are computed to quantify connectivity, complexity, and centrality. The results reveal meaningful patterns that bridge ring theory and graph theory.
The government issues the Vehicle Registration Certificate (STNK), an official document that certifies a motorized vehicle's identity and authenticity. Pamekasan Regency is one of the regencies in East Java Province that frequently suffers losses associated with Vehicle Registration Certificates (STNK). Consequently, it is essential to predict the amount of car registration losses so that the Pamekasan regional administration can use the information to lower the losses. The Double Exponential Smoothing and Double Moving Average techniques were used in this study to forecast the amount of vehicle registration losses. According to the research findings, the smoothing parameters 𝑎 = 0.3 and 𝛾 = 0.025 had the lowest MAPE value from the Double Exponential Smoothing method, with a MAPE value of 49.4082%. The double moving average method's smallest MAPE, 𝑘 = 3, has a MAPE value of 31.53215%. The twofold moving average approach is the best way to forecast the loss of car registration in Pamekasan, according to the comparison's findings.
The Consumer Price Index (CPI) is a crucial measure of inflation and the cost of living within a specific region. Accurate CPI forecasts are essential for policymakers, businesses, and stakeholders to make informed decisions. This study utilizes the Double Exponential Smoothing (DES) method to forecast the CPI for Banyumas Regency in January 2025, employing monthly CPI data from January 2020 to December 2024. The DES method was selected due to the observed upward trend in historical CPI data. Python programming was employed to optimize the smoothing parameters α and β, and the results were evaluated using Mean Absolute Deviation (MAD), Mean Squared Error (MSE), and Mean Absolute Percentage Error (MAPE). The forecasted CPI for January 2025 is 106.36, with high accuracy indicators, including a MAPE of 0.26%, demonstrating that DES is a reliable model for CPI forecasting in Banyumas Regency.
Indonesia is one of the countries that ratified the Paris Agreement, a legally binding international treaty under the United Nations Framework Convention on Climate Change (UNFCCC) regarding greenhouse gas emissions. In line with this commitment, Indonesia is expected to prioritize emission control in sectors that contribute significantly to national emission levels. This study applies the Self-Organizing Map (SOM), a type of neural network, to cluster emission data by sector based on similarity patterns, aiming to identify priority sectors for emission control in Indonesia. The results indicate that the highest-emitting sectors are: Processes for Carbon Dioxide (CO₂), Transport for Methane (CH₄), Processes for F-Gases, and Agriculture for Nitrous Oxide (N₂O). These findings can inform government efforts to prioritize emission control policies in the Processes, Transport, and Agriculture sectors, tailored to each dominant gas type. Such recommendations are essential to support data-driven decision-making, improve national emission control strategies, and strengthen Indonesia’s position in meeting its Nationally Determined Contributions (NDCs) under the Paris Agreement. Model validation using Quantization Error (QE) produced values of 0.0218 for CO₂, 0.0207 for CH₄, 0.0040 for F-Gases, and 0.0171 for N₂O. These low values indicate high mapping accuracy and confirm that SOM is effective in capturing the distribution patterns of emission data, thus providing a scientific basis for designing more targeted mitigation strategies.
This study uses Google Earth Engine, a cloud computing platform, to examine variations in land surface temperature in East Lombok Regency between 2010 and 2020. This study uses MODIS satellite data and is analyzed using Google Earth Engine by adapting a mathematical method—namely, the Random Forest Algorithm from discrete mathematics. According to the results, the temperature increased from its lowest point in 2010 (14.32°C) to its maximum point in 2020 (36.19°C), rising to 16.67°C and 37.74°C. Due to residential growth, Wanasaba, Pringgabaya, and Sambelia saw the biggest increases. Comprehensive temperature monitoring is made possible by Google Earth Engine, which facilitates the effective processing of large-scale spatial data. These results offer a scientific foundation for policy decisions and are essential for environmental management and climate change mitigation. In addition to supporting environmental monitoring initiatives, this study provides a reference for related studies in other areas dealing with issues related to land use and climate change. This research is important for the Central Lombok government as a basis for mitigation efforts in responding to temperature changes and their implications for land use change.
Graph theory offers a robust framework for examining algebraic structures, especially rings and their elements. This paper focuses on the nilpotent graph of rings of the form Zpk, where p is a prime and k∈N, investigating both their structural and numerical properties. We begin by characterizing the nilpotent elements in these rings and examining their relationship to ring ideals. The study then presents theoretical results on key graph invariants, including connectivity, chromatic number, clique number, and specific subgraph configurations. To complement these, we also analyze numerical invariants such as edge count and degree distribution, which reveal deeper connections between ring-theoretic and graph-theoretic properties. Our results highlight consistent structural patterns in nilpotent graphs of Zpk and provide a concrete contribution to algebraic graph theory by bridging properties of commutative rings and their associated graphs.
This study evaluates the technical efficiency of subsidized fertilizer use in rice production across villages in Bangsri Sub-district, Jepara Regency, using the output-oriented CCR model of Data Envelopment Analysis (DEA). The research was motivated by the crucial role of fertilizers in sustaining rice productivity and the persistent issue of inefficient allocation and utilization of subsidized inputs. Secondary data for 2023 were obtained from the Balai Penyuluh Pertanian of Bangsri Sub-district and the Badan Pusat Statistik of Central Java. Input variables included the quantity of subsidized urea, NPK, and granular organic fertilizers, as well as cultivated land area; the output variable was rice production, calculated under the assumption of constant provincial average productivity of 49.26 quintals/ha. All villages in the sub-district were treated as Decision-Making Units (DMUs). The DEA results revealed that only Kedungleper achieved full efficiency (score = 1.00), while Jerukwangi was near the frontier (score = 0.96). Most villages scored between 0.80 and 0.89, indicating substantial room for optimization. The observed inefficiencies may be attributed to mismatches in fertilizer dosage and composition, suboptimal timing and application methods, and local agronomic constraints. Recommended strategies include benchmarking efficient villages, revising fertilization packages and schedules based on site-specific conditions, and strengthening plot-level extension services to ensure that inputs are effectively translated into yield gains. These findings provide actionable insights for improving resource-use efficiency and guiding targeted fertilizer subsidy policies.
Final semester grades are an important component for students to obtain a pass in completing a course. The program for determining final semester grades using fuzzy Mamdani can be used to facilitate the calculation of final semester grades. This research aims to determine the results of applying the Mamdani fuzzy system method in determining the final semester grades of students at UIN Walisongo Semarang. The Mamdani fuzzy system method was chosen as the method for calculating final semester grades along with MAPE (Mean Absolute Percentage Error) calculations. In accordance with the lecture contract for the computational mathematics course, several input variables were found to be used in the research, namely structured assignment grades (20%), independent assignment grades (30%), mid-semester exam grades (25%), and final semester exam scores (25%). The data is processed in several steps, namely creating fuzzy membership sets and functions, creating fuzzy rules, fuzzification, and defuzzification. After calculating with the Mamdani method fuzzy system, the next step is to calculate the MAPE value and display the results. The MAPE value obtained from research with 46 data was 2.074; This means that according to the MAPE criteria it produces accurate data. This proves that the Mamdani fuzzy system method can be applied to calculate students' final semester grades.
Speech recognition is one of the most popular research fields, one of which is about emotion identification. Voice-based emotion identification is carried out to determine the pattern of emotions using the depth analysis mechanism of voice signal development and feature extraction that carries the emotional characteristic parameters of the speaker's voice. Furthermore, the emotional characteristics of the speaker's voice are classified using an artificial neural network method to recognize patterns. In this study, emotion identification from voice signal data is classified into angry, sad, happy, and neutral emotions. The stages of voice-based emotion identification, including the feature extraction stage using the mel frequency cepstral coefficient, produce coefficient values, which will be used in the identification stage using the Self Organized Maps method on the Radial Basis Function.
The zero-divisor graph of a commutative ring is a graph where the vertices represent the zero-divisors of the ring, and two distinct vertices are connected if their product equals zero. This study focuses on determining general formulas for the Szeged index and the Padmakar-Ivan index of the zero-divisor graph for specific commutative rings. The results show that for the first case of ring, the Szeged index is exactly half of the Padmakar-Ivan index. For the second case, the Szeged index is consistently greater than the Padmakar-Ivan index. These findings enhance the understanding of how the algebraic structure of rings influences the topological properties of their associated graphs.
Inflation is one of the important aspects that is used as a benchmark to see economic growth and economic conditions in each country. Inflation has resulted in increasing public expenditure in meeting basic needs. Inflation must be controlled to maintain the economic stability of a country, including Indonesia. Therefore, there is a need for a model that can forecast the inflation rate in Indonesia. The aim of this research is to create a model that can predict future inflation levels so that it can help the government in determining policies related to controlling inflation in Indonesia. The data used is monthly inflation data in Indonesia for 19 years from March 2007- October 2023 in percentage form. The forecasting model used in this study is the ARIMA-GARCH model. The ARIMA model is a time series model used to forecast future data based on past data. While GARCH is a time series model used to overcome heteroscedasticity in the ARIMA model. Inflation data will be modeled using the ARIMA model and then continued by modeling the residuals using the GARCH model if heteroscedasticity occurs in the ARIMA model residuals. Based on data analysis that has been done, the best model for inflation forecasting cases in Indonesia is the ARIMA (2,0,2) - GARCH (0,1) model with a MAPE value of 17.78%.
Tuberculosis (TBC) is an infectious disease affecting the respiratory system, caused by the bacterium Mycobacterium tuberculosis. Tuberculosis (TBC) remains a global concern, and to date, no country is completely free from TB. This disease continues to be one of the leading causes of mortality. Therefore, it is essential to categorize the spread of TBC. The percentage of identity in genetic codes will reveal the proportion of mutations. The percentage of identity in genetic codes will demonstrate that, although the symptoms caused by a disease may be quite similar, the protein sequences are not necessarily the same. In this study, the researchers employed the Hierarchical Clustering method, integrating the Needleman-Wunsch and Jukes-Cantor algorithms, resulting in two groups. The first group consists of 9 interconnected rows, while the second group consists of 7 interconnected rows.
In chemistry, graph theory has been widely utilized to address molecular problems, with numerous applications in graph theory and ring theory within this field. One of these applications involves topological indices that represent chemical structures with numerical values. Various types of topological indices exist, including the Wiener index, the first Zagreb index, and the hyper-Wiener index. In the context of this research, the values of the Wiener index, the first Zagreb index, and the hyper-Wiener index for zero-divisor graphs on the ring of integers modulo a prime power order will be explored through a literature review and conjecture.
The main goal of every individual in life is to achieve happiness, a subjective concept. To measure happiness, one approach used is the life satisfaction dimension. In multivariate analysis, the biplot method emerges as a useful tool to map variables and objects of observation simultaneously in a two-dimensional graph. This study was conducted with the aim of analyzing biplots on the happiness index, with the dimension of life satisfaction as the main variable. The data used comes from the Central Bureau of Statistics (BPS), specifically related to the Life Satisfaction Dimension of the Happiness Index in 2021. By conducting careful biplot analysis, the pattern of relationships between provinces in the context of happiness can be revealed. The results of the biplot analysis show that provinces in the same quadrant have closer similarities in happiness characteristics than provinces in different quadrants.
The high number of people with disabilities is one of the problems faced by the Indonesian government, especially in Java Province. After West Java Province, East Java Province is in second place as the province with the highest rate of people with disabilities in Indonesia. Disabled people are people with physical disabilities such as not being able to walk, not being able to talk, not being able to see, and so on. The aim of this research is to group districts in East Java Province based on types of disabilities with the hope of facilitating activities in fulfilling the rights of people with disabilities in East Java Province. The grouping was carried out in order to determine the characteristics of each cluster using so that the optimal k-means method was used for clustering using the Euclidean distance method with cluster 1 in 29 districts and cluster 2 in 9 districts. The most optimal single linkage uses the Euclidean distance method with cluster 1 having 8 districts and cluster 2 having 30 districts. From the results of the validity index values, it was found that the single linkage method had the smallest validity value of the icdrate method compared to the k-means method.
This research investigates the existence and uniqueness of solutions to homogeneous linear equations in supertropical algebra. We analyze the structure of supertropical matrices to identify the conditions in which nontrivial solutions exist for the system of equations A⊗𝒙 ⊨ 𝜀, where A is a matrix over a supertropical semiring and x is a vector. By applying determinant-based criteria, we demonstrate how tropical and supertropical values influence the solution space. The research applies theorems that determine the presence of trivial and nontrivial solutions and uses examples to illustrate practical methods for solving homogeneous matrix systems. This highlights the distinct characteristics of supertropical algebra compared to classical linear algebra. Our findings provide a deeper insight into solution behaviors in supertropical systems, paving the way for further research in tropical mathematics.
