Universitas Islam Kuantan Singingi: E-Journals
Not a member yet
1863 research outputs found
Sort by
Performance Comparison of K-Means Algorithm and BIRCH Algorithm in Clustering Earthquake Data in Indonesia with Web-Based Map Visualization
Get PDFThis study applies the K-Means and BIRCH algorithms to cluster earthquake data in Indonesia based on geographic coordinates (latitude and longitude), depth, and magnitude from 2008 to 2023. Due to its position at the intersection of three major tectonic plates, Indonesia is highly prone to earthquakes, making the mapping of vulnerable regions essential for disaster risk reduction. K-Means is selected for its simplicity and clustering effectiveness, while BIRCH is known for its scalability and efficiency in processing large datasets. The clustering process involves data preprocessing and normalization, followed by determining the optimal number of clusters using the Elbow method. Initial findings indicate that K-Means produces more distinct and well-separated clusters than BIRCH, with Silhouette Scores of 0.3501 and 0.2247, respectively. However, after expanding the dataset to 121,123 records and incorporating additional attributes such as mag_type, phasecount, and azimuth_gap, BIRCH demonstrated a significant improvement in performance, achieving a Silhouette Score of 0.3489—surpassing K-Means, which dropped to 0.1293. These results suggest that BIRCH is more effective for clustering large and complex datasets. The final clustering results are visualized on a web-based map to support spatial analysis and the identification of earthquake-prone zones
Integration of Machine Learning Models Random Forest and XGBoost for Credit Card Fraud Detection in a Python Flask-Based Application
Get PDFCredit card fraud is one of the major challenges in modern digital payment systems. The increasing volume of online transactions raises the potential for unauthorized use of cardholder data. This research aims to develop a robust and accurate fraud detection system by integrating two machine learning algorithms, Random Forest and XGBoost, both of which are known for their high performance in data classification. The research process begins with the collection and preprocessing of credit card transaction data, followed by model training using the selected algorithms. The model’s performance is evaluated using metrics such as accuracy, precision, recall, and F1-score. To enable real-time application, the model is implemented in a web-based system using the Python Flask framework, allowing direct integration into financial transaction environments. The need for adaptive systems that can respond to emerging fraud patterns serves as a key motivation for this study. By combining two complementary algorithms within a single web application platform, the system is expected to detect fraudulent activities quickly and accurately. The expected outcomes of this research include: (1) an optimized fraud detection model based on Random Forest and XGBoost, (2) a prototype web application developed with Python Flask for system implementation, and (3) a scientific publication describing the development and results of the proposed system. The targeted outputs are a publication in a nationally accredited journal (Sinta 4) and intellectual property registration. This research is expected to provide a significant contribution to preventing credit card fraud through the effective application of machine learning technologie
Implementation of the Website on the Raudhatul Mukhlisin Mosque Fund, Sako District Using the Waterfal Method
Get PDFMosques play a central role in Muslim community life, not only as places of worship but also as centers for social and financial activities, such as donations, alms management, and dissemination of mosque-related information. However, in the current era of rapid technological development, many mosques still rely on manual systems for financial management and information delivery, which are prone to recording errors, calculation inaccuracies, data loss, and limited transparency. This condition can reduce public trust and hinder effective mosque management. Therefore, technological innovation is needed to support transparent, accurate, and efficient mosque administration. This research aims to assist the management of Raudhatul Mukhlisin Mosque in improving the efficiency and accuracy of mosque financial data management through the development of a website-based information system. The system was developed using the Waterfall method, which includes requirement analysis, system design, implementation, testing, and maintenance. This study applies qualitative research methods with data collection techniques including observation and literature review. The developed system utilizes PHP, HTML, and MySQL, and system testing was conducted using the Black Box method. The results show that the proposed system facilitates data recording, financial reporting, and information access, while enhancing transparency and accountability for mosque administrators and worshippers
Diversity of Seedling Species as an Indicator of Natural Regeneration in the Imbo Putui Customary Forest, Riau Province
Get PDFBiodiversity is crucial for meeting the diverse needs of living organisms. As the human population grows, so do the demands on forests. Without proper management, large-scale exploitation of forest resources is risky. To ensure the sustainability of nature, it is essential to implement regeneration patterns in forest areas, such as natural regeneration. This study aimed to assess plant regeneration in the Imbo Putui Customary Forest area in Kampar Regency. The research utilized Systematic Sampling with Random Start to record seedlings in the study plot. Data analysis included the Important Value Index (INP), Species Diversity Index, Evenness Index, and Species Richness Index. The study identified 27 plant species, with Lalan (Santiria laevigata) being the dominant species. The diversity and species richness indices indicated moderate results, while the evenness index showed high evenness levels
Effectiveness of Biological Agents in Improving the Growth of Cayenne Pepper (Capsicum frustescens) in Alfisol Soil
Get PDFTuban Regency is a major center for cayenne pepper production, but it is currently experiencing a decline in production due to the shrinking productive land area. As a result, farmers are opening new land in forest areas dominated by alkaline alfisol soil that lacks phosphorus elements. This study investigates the impact of biological agents Bacillus subtilis and CMA on the growth of cayenne pepper plants in alfisol soil. The study utilized a randomized block design with 8 treatments and 3 replications, resulting in a total of 24 beds: A0 (Control); A1 (SP-36); A2 (Bacillus subtilis); A3 (CMA); A4 (SP-36 + Bacillus subtilis); A5 (SP-36 + CMA); A6 (Bacillus subtilis + CMA); A7 (SP-36 + Bacillus subtilis + CMA). Plant growth measurements included dry weight, net assimilation rate, and crop growth rate (CGR). The research findings indicate that the combination of biological agents Bacillus subtilis and CMA in the A7 treatment (SP-36 + Bacillus subtilis + CMA) had the most significant impact on the growth of cayenne pepper plants across all parameters. This was confirmed by the results of the BNT test, which showed improvements in dry weight (23.253 grams), net assimilation rate (2.7950), and crop growth rate (9.790)
Effectiveness of Liquid Organic Fertilizer Application of Lamtoro Leaves and Quail Manure Fertilizer on Melon Plants (Cucumis melo L) Growth and Production
Get PDFThe melon crop commodity has great potential to meet public demand. One way to improve melon quality is using organic fertilizer, which enhances soil properties and provides plant nutrients. This study utilized a factorial Randomized Block Design with two factors. The first factor was the POC of Lamtoro leaves (L) with 4 levels: 0 ml/1L water/plot, 200 ml/1L water/plot, and 400 ml/1L water/plot. The second factor was quail manure with 4 levels: 0 kg/plot, 1 kg/plot, 2 kg/plot, and 3 kg/plot. Parameters measured included plant height, number of leaves, flowering time, stem diameter, fruit diameter per sample, fruit weight per sample plant, and fruit weight per plot. The results showed that applying POC fertilizer from Lamtoro leaves and quail manure had no significant effect on plant height, number of leaves, flowering time, and stem diameter. However, it had a significant effect on fruit weight per sample plant, a very significant effect on fruit diameter per sample, and fruit weight per plot
Adaptation of Rice Varieties (Oryza sativa L.) in Paddy Fields Rain Feeding through The Use of Ameliorant in Lahat Regency
Get PDFRice is a food crop commodity that serves as the staple food for the Indonesian population. This study examines the adaptation of various rice varieties with the addition of ameliorants on growth and yield in rainfed paddy fields. The research was conducted in Lahat District, Lahat Regency, from January to May 2024, utilizing a split-plot design with 12 treatment combinations, each replicated three times. The main plot treatments consisted of ameliorants, while the subplot treatments involved different rice varieties. The observed parameters included plant height (cm), number of tillers, number of productive tillers, panicle length (cm), flowering age (days after sowing), harvest age (days after sowing), total grains per panicle (grams), percentage of empty grains (%), 1000-grain weight (grams), and productivity (ton/ha). The results indicated that applying ameliorants, such as lime and solid organic fertilizer, yielded the most favorable outcomes for rice plant growth. Tabular analysis revealed that the Situ Bagendit variety exhibited the highest productivity compared to other varieties. Furthermore, the combination of ameliorants, specifically lime and organic fertilizer, along with the Situ Bagendit variety, achieved the highest paddy productivity at 5.13 tons per hectare
Increasing the Growth of Upland Rice (Oryza sativa L.) on Ultisol Soil with the Provision of Solid Compost and Boiler Ash
Get PDFRice (Oryza sativa L.) is the primary food commodity for 98.86% of the Indonesian population. To meet national demand, rice production can be enhanced through the extensification and intensification of podzolic land using soil conditioners such as solid compost and oil palm boiler ash. This study aims to determine the interaction between solid compost and oil palm boiler ash, assess the effect of each treatment, and identify the optimal doses of solid compost and oil palm boiler ash for the growth and yield of upland rice cultivated in podzolic soil. The research was conducted using a factorial, completely randomized design (CRD). Factor I, solid compost, included the following treatments: 0 g per polybag (0 t.ha⁻¹), 12.5 g per polybag (2.5 t.ha⁻¹), 25 g per polybag (5 t.ha⁻¹), and 37.5 g per polybag (7.5 t.ha⁻¹). Factor II, boiler ash, comprised the following treatments: 0 g per polybag (0 t.ha⁻¹), 5 g per polybag (1 t.ha⁻¹), 10 g per polybag (2 t.ha⁻¹), and 15 g per polybag (3 t.ha⁻¹). The results indicated that a solid compost dose of 7.5 t.ha⁻¹ produced the best growth across all observed parameters. Additionally, a boiler ash dose of 2 t.ha⁻¹ was optimal for increasing the number of productive tillers, the number of whole grains per panicle, and the weight of dry milled grain per polybag. Conversely, a boiler ash dose of 3 t.ha⁻¹ was most effective in enhancing plant height, the maximum number of tillers, panicle emergence age, harvest age, the percentage of full grains, and the weight of 100 full grains
Dominance of Understory Vegetation and Biomass Production of Oil Palm Plantations on Mineral Land
Get PDFThe understory vegetation of oil palm plantations varies across different types of land. The biomass of this vegetation plays a crucial role in maintaining the ecological balance of oil palm plantation ecosystems. This study aims to identify the types of understory vegetation and calculate biomass production on the mineral land of PT. Rigunas Agri Utama's oil palm plantations. The research was conducted in August 2024 using direct observation methods. Observations of understory vegetation were carried out on 45 sample plots utilizing the quadrat method and the Plantnet application, with biomass measurements taken using the destructive sampling method. The results indicated the presence of 27 understory vegetation species with varying compositions. The most dominant species was Mitracarpus hirtus (L.) DC. The highest density, frequency, and dominance values were exhibited, with a species dominance ratio (SDR) of 35%. Understory vegetation primarily comprises broadleaf species and grasses, with a significant proportion being perennial plants that enhance ecosystem stability. The total biomass production of understory vegetation reached 5,943 kg over 12 hectares, resulting in carbon stocks of 2,793 kg C per 12 hectares. The species contributing the most to biomass include Mitracarpus hirtus, Cyperus rotundus, and Eleusine indica. The findings of this study indicate that the total carbon stock of understory vegetation in oil palm plantations is approximately 232.7 kg C per hectare. In comparison, carbon stocks in understory vegetation within agricultural ecosystems, such as oil palm plantations, typically range from 0.18 to 1.00 tons C per hectare (180 to 1,000 kg C per hectare), suggesting a strong potential for carbon storage in the oil palm plantations of PT. Rigunas Agri Utama
Impact of Regenerative Agriculture on Soil Biological Performance in Arabica Coffee (Coffea arabica) Cultivation
Get PDFSoil health is a crucial factor in the sustainability of Arabica coffee production, particularly in addressing the challenges of land degradation caused by conventional agricultural practices. One practical approach to naturally enhance soil fertility is implementing a regenerative farming system, which focuses on increasing the diversity of soil microbes to support a healthy and productive ecosystem. This study aims to analyze and compare the diversity of soil microbes in Arabica coffee fields managed under regenerative farming systems versus those under conventional farming systems. It will identify the dominant types of microbes in each system and examine how their presence influences soil fertility. Additionally, the study will assess the impact of regenerative farming on the balance of the soil microbial ecosystem and the health of coffee plants. The methodology employed is comparative, involving soil sampling through random sampling techniques. Microbial diversity will be analyzed using culture methods, with soil microbial observation parameters including bacteria, fungi, phosphorus-solubilizing bacteria, nitrogen-fixing bacteria, respiration rates, and the carbon-to-nitrogen (C/N) ratio. Laboratory data will be analyzed using comparative statistical tests, specifically the t-test. The study aimed to identify microbial distribution patterns using PCA-Bi Plot analysis. The results indicated that the total number of bacteria, fungi, total microbes, and soil respiration rates were significantly higher in the regenerative farming system than in the conventional system. The dominant soil microbes in the regenerative farming system included nitrogen (N) fixing bacteria and decomposer fungi. A strong positive correlation (r = 0.938, p < 0.01) was observed between total microbes and soil respiration. The regenerative farming system not only increases the number of soil microbes but also enhances the biological activity of the soil. These findings underscore the potential of regenerative agriculture as a viable alternative for improving soil quality in Coffea arabica cultivation, aligning ecological benefits with agricultural productivity