Claim Missing Document
Check
Articles

Found 22 Documents
Search

Forecasting of Clean Water Usage by Observing Trend Pattern using Time Series Method Mahmudi, Mahmudi; Nurillah, Usmau Lidya; Rusdiana, Siti; Saputra, T Murdani
Transcendent Journal of Mathematics and Applications Vol 2, No 1 (2023)
Publisher : Syiah Kuala University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24815/tjoma.v2i1.31377

Abstract

Population growth will increase the need for clean water. One of the clean water providers in the city of Banda Aceh is Local Water Supply Utility (PDAM) Tirta Daroy. To anticipate the surge in demand for clean water, PDAM needs to know the need for clean water in the future. One of the steps that can be taken is to do forecasting with the double exponential smoothing and triple exponential smoothing method. The smallest error value can be found using the mean absolute percentage error (MAPE) formula. Based on research, the double exponential smoothing method provides the most accurate forecast data when the parameter value 0.6 with an error of 3.5%. While the triple exponential smoothing method, the most accurate forecast data is obtained when the alpha value is 0.4 with an error of 3.55%.
Application of The Exponential Smoothing Method in Predicting The Visit of Foreign Tourists to Indonesia Rusdiana, Siti; Rahayu, Latifah; Asmanidar, Asmanidar
Transcendent Journal of Mathematics and Applications Vol 1, No 1 (2022)
Publisher : Syiah Kuala University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24815/tjoma.v1i1.28843

Abstract

Indonesia is rich in natural beauty, diverse ethnic groups, cuisines, and languages, making it one of the most popular destinations for both domestic and international tourists. The purpose of this study is to forecast the number of foreign tourist visitors from 2020 to 2021. The government can improve facilities or infrastructure while also preserving the beauty and culture of Indonesia's various ethnic groups. This study will investigate 101 foreign countries that visited Indonesia using one of the Exponential Smoothing methods. In forecasting, the Triple Exponential Smoothing method has three smoothing times. Forecasting in 101 foreign tourists visiting Indonesia yields different parameter results because each result has a different smoothing value. Once the parameters ranging from 0.1 to 0.9 is close to forecasting results, there are close to the actual value. The search ends at one of these parameters because it already yields the expected results to calculate the error value using the MAPE method. There were 20 foreign tourists selected based on the average number of visits to Indonesia.
Determining The Selling Price of Thrift Using The Fuzzy Sugeno Method Radhiah, Radhiah; Rusdiana, Siti; Hamdi, Syaiful; Nurmaulidar, Nurmaulidar; Syahrini, Intan; Mahmudi, Mahmudi; Ikhwan, Muhammad
Indonesian Journal of Applied Mathematics Vol. 3 No. 2 (2023): Indonesian Journal of Applied Mathematics Vol. 3 No. 2 October Chapter
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat (LPPM), Institut Teknologi Sumatera, Lampung Selatan, Lampung, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35472/indojam.v3i2.1598

Abstract

The use of thrift goods in life has the effect of saving and loving the environment. Many of these objects are difficult to degrade in nature and are nevertheless thought to have economic worth, for example used electronic equipment such as laptops. On the other hand, in today's classroom environment, laptops are quite important. Even the most recent computers with good features are fairly costly, thus used laptops are one answer to this. The seller's selling price usually only takes a few elements into account, therefore the price set does not always match the requirements. The aim of this paper is to apply the zero order Sugeno fuzzy approach to determine the selling price of old laptop. The system is built with characteristics such as laptop age, physical condition, RAM, new purchase price, and used selling price. The simulation findings suggest that fuzzy logic employing the zero-order Sugeno approach can be utilized to determine the selling price of old laptop while accounting for the affecting variables.
Improving the Classification Performance of SVM, KNN, and Random Forest for Detecting Stress Conditions in Autistic Children Melinda, Melinda; Yunidar, Yunidar; Miftahujjannah, Rizka; Rusdiana, Siti; Amalia, Amalia; Qadri Zakaria, Lailatul
International Journal of Engineering, Science and Information Technology Vol 5, No 4 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i4.1206

Abstract

This paper addresses the critical challenges of managing stress in autistic children by introducing an innovative deployable system designed to detect signs of stress through continuous monitoring of physiological and environmental indicators. The system, implemented as a convenient portable detection system, measures key parameters such as heart rate, body temperature and skin conductance. The data is accessed in real-time and displayed on the Blynk application with an IoT system and viewed remotely via an Android device, allowing caregivers to receive instant notifications upon detection of potential stress symptoms. This timely alert system enables rapid intervention, potentially reducing stress intensity and providing peace of mind to caregivers. The study further compares three powerful data analysis methods namely Support Vector Machine (SVM), K-nearest neighbors (KNN) and Random Forest (RF) in interpreting the collected sensor data. The SVM-based system achieved a fairly good detection accuracy of 90%, KNN also showed excellent results of 92% while the Random Forest-based system showed superior performance with an impressive accuracy of 95%. These findings suggest that the Random Forest method exhibits a superior level of effectiveness in accurately predicting the onset of stress conditions., providing the importance for technological advancements that can be applied in supporting better management of autism-related behavioral defenses.
COMPARISON OF WEIGHTED MARKOV CHAIN AND FUZZY TIME SERIES-MARKOV CHAIN METHODS IN AIR TEMPERATURE PREDICTION IN BANDA ACEH CITY Rusdiana, Siti; Febriana, Diana; Maulidi, Ikhsan; Apriliani, Vina
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 17 No 3 (2023): BAREKENG: Journal of Mathematics and Its Applications
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol17iss3pp1301-1312

Abstract

Air temperature prediction is needed for various needs such as helping plan daily activities, agricultural planning, and disaster prevention. In this research, Weighted Markov Chain (WMC) method and Fuzzy Time Series-Markov Chain (FTS-MC) method are applied to predict the weekly air temperature in Banda Aceh city. The purpose of this study is to find out how the results of the application and comparison of the accuracy of the WMC method and the FTS-MC method on weekly air temperature prediction in Banda Aceh City. The prediction result of air temperature in Banda Aceh city using the WMC method for the next three weeks obtained an air temperature of 26,5℃. The prediction results of air temperature in Banda Aceh city using the FTS-MC method for the next three weeks obtained predicted values of 26,66℃ for the 105th week, 26,79℃ for the 106th week, and 26,83℃ for the 107th week. The MAPE accuracy level of the WMC method is 1,5% and the FTS-MC method is 1,7%. This shows that the MAPE of the WMC method is smaller than the FTS-MC method so it can be concluded that air temperature prediction using the WMC method is better than the FTS-MC method.
PREDICTING LAND USE CHANGES USING MARKOV CHAIN ANALYSIS AND HIERARCHICAL ANALYSIS OF PUBLIC SERVICE CENTERS IN BANDA ACEH CITY Rahmaniar, Meutia Hanum; Rusdiana, Siti; Zahnur, Zahnur
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 18 No 4 (2024): BAREKENG: Journal of Mathematics and Its Application
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol18iss4pp2319-2328

Abstract

The city of Banda Aceh, as the center of development in its region, is faced with a series of complex problems, one of which is the lack of optimal distribution of public service centers throughout the city. Banda Aceh City Central Statistics Agency (BPS) documents 2012-2022 and Banda Aceh City Spatial Plan (RTRW) documents 2009-2029 related to this research. Data in tabulated and descriptive form includes geographical conditions of the research area, land use area, types of facilities and their numbers, population, and distance between areas, and maps related to the research. This study aims to see land use conditions using the markov chain method and provide an overview of the public service center system of Banda Aceh City using the Scalogram method, centrality index, and gravity. Based on Markov chain analysis, land use predictions indicate that residential areas, offices and trade, tourism, worship, and sports facilities will continue to increase, while water bodies, green open spaces (RTH), and non-green open spaces (RTNH) will continue to decline. Predictions until 2039 show that conditions have begun to stabilize. Scalogram analysis takes into account hierarchy based on the type of facilities available, centrality index that calculates hierarchy based on many available facilities, and gravitational interaction that takes into account the strength of interaction between sub-districts shows that Kuta Alam District has the potential to become a major service center in Banda Aceh City. This sub-district has the most complete facilities, supported by the highest interaction value.
Mobile Application Development for Facial Classification of Autistic Children Based on MobileNet-V3 Ramadhan, Irsyan; Melinda, Melinda; Yunidar, Yunidar; Acula, Donata D; Miftahujjannah, Rizka; Rusdiana, Siti; Zainal, Zulfan
JURNAL INFOTEL Vol 17 No 3 (2025): August
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v17i3.1363

Abstract

Early detection of autism spectrum disorder (ASD) is crucial to support timely interventions that can improve children’s cognitive and social development. However, conventional approaches still rely on subjective observations and parental reports. This study proposes the development of a Flutter-based mobile application for face classification of autistic and non-autistic children using the MobileNetV3-Small architecture. The dataset contains 600 original facial images of children aged 4 to 14 years (300 autistic and 300 non-autistic), which were expanded to 1,860 images through augmentation techniques such as Gaussian noise addition, flipping, and contrast adjustment. The model was trained using transfer learning and optimized with the SGD optimizer and sigmoid activation function. During training, the model achieved a training accuracy of 95.27% and a validation accuracy of 97.92%, indicating effective learning with minimal overfitting. Evaluation on the test data showed perfect performance, with accuracy, precision, recall, and F1-score all reaching 100%. The model was then converted to TensorFlow Lite format to allow on-device inference on mobile platforms. The app enables users to upload photos via camera or gallery and instantly receive classification results, which are also saved to Firebase for history tracking. Testing showed a fast response time (1–2 seconds) and a smooth, user-friendly experience. These results highlight the potential of the system as a lightweight, efficient, and accessible facial image-based ASD screening tool, particularly in regions with limited access to specialized healthcare. Future work should include validation using larger and more diverse datasets across different demographics to ensure model robustness, fairness, and generalizability in real-world environments.
Application of Extreme Learning Machine (ELM) for Water Level Prediction in Krueng Peusangan River Basin (2014–2023) Aznita, Meri; Rusdiana, Siti; Ramli, Ichwana; Izzaty, Atika; Ferijal, T
Jurnal Teknik Pertanian Lampung (Journal of Agricultural Engineering) Vol. 14 No. 5 (2025): October 2025
Publisher : The University of Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jtepl.v14i5.1638-1649

Abstract

The Krueng Peusangan Watershed in Aceh Province is highly vulnerable to flooding, with 20.39% of its area classified as flood-prone, particularly in Bireuen Regency. This study aims to develop a water level prediction model using the Extreme Learning Machine (ELM), a type of Artificial Neural Network known for its computational efficiency and ability to handle uncertainty in hydrological data. The model was trained using water level data from the Krueng Peusangan River from January 2014 to June 2023. The results show a Mean Squared Error (MSE) of 0.063, indicating high predictive accuracy. Compared to conventional methods, ELM delivers faster computation and better precision. This research contributes to the development of data-driven flood early warning systems, supports adaptive and sustainable water resource management, and offers potential for replication in other watersheds with similar characteristics. Furthermore, the model provides a scientific basis for formulating disaster risk reduction policies leveraging artificial intelligence technologies. The promising accuracy of ELM supports its potential integration into real-time flood early warning systems and long-term adaptive water resource management in vulnerable river basins.
Application Of Hungarian Method In Optimizing The Scheduling Of Employee Assignment And Profit Of Home Industry Production Rusdiana, Siti; Oktavia, Rini; Charlie, Empya
Journal of Research in Mathematics Trends and Technology Vol. 1 No. 1 (2019): Journal of Research in Mathematics Trends and Technology (JoRMTT)
Publisher : Talenta Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32734/jormtt.v1i1.754

Abstract

This research has a purpose to optimize the scheduling of employees in an embroidery company for doing certain tasks using Hungarian method, as well as analyzing the sensitivity of the optimal solution if there is a reduction on the employees’ time to finish the tasks. The Hungarian method was applied on the assignment of workers in embroidery process involving 11 employees and 10 tasks. The optimal scheduling result minimizes the time of the embroidery production of the company. The optimal scheduling result found the optimal assignment of each worker to the tasks with the total work time is 13,7 hours. After the Hungarian method was applied, the company got the increasing revenue as much as 9,09 %. The sensitivity analysis was conducted by reducing the time of the employees take in embroidery the bags. The results of the sensitivity analysis are some boundaries for basis and non basis variables to maintain the optimal solution.
Comparison of Rainfall Forecasting in Simple Moving Average (SMA) and Weighted Moving Average (WMA) Methods (Case Study at Village of Gampong Blang Bintang, Big Aceh District-Sumatera-Indonesia Rusdiana, Siti; Syarifah Meurah Yuni; Delia Khairunnisa
Journal of Research in Mathematics Trends and Technology Vol. 2 No. 1 (2020): Journal of Research in Mathematics Trends and Technology (JoRMTT)
Publisher : Talenta Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32734/jormtt.v2i1.3753

Abstract

The changing climate causes rainfall to vary from period to period. This change has an impact on society, especially in agriculture such as crop failure. This study aims to predict rainfall in 2018 and 2019 with the Simple Moving Average (SMA) method and the Weighted Moving Average (WMA) method. Based on 2004-2018 data, the dry season occurs in February-October and the rainy season in November-January. The level of validation of forecasters in 2018 according to each the SMA method and the WMA method were 43.43% and 40.69%, respectively. Both of these methods are low and reasonable or acceptable. Based on the SMA method, the division of the dry season in 2019 is estimated in February-October while the distribution of the rainy season in the same year is in December-January. Based on the WMA Method that the distribution of the dry season is estimated in February-April, June-September and the rainy season in October-January and May.