Publication Search

This study aims to optimize the architecture of Artificial Neural Networks (ANN) for rainfall prediction using meteorological data from Indonesia, which is known for its complex and highly variable climate patterns. Climatic variables such as temperature, humidity, air pressure, wind speed, and historical rainfall records serve as the main input features to evaluate the performance of various network configurations. Optimization is carried out by determining the appropriate number of neurons, hidden layers, activation functions, and training algorithms to enhance prediction accuracy. Model evaluation employs indicators such as Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) to ensure output stability. The findings indicate that a multilayer architecture combined with optimized parameters significantly improves the network’s ability to capture non-linear patterns in Indonesia’s tropical rainfall data. The optimized model produces more stable and accurate predictions compared to standard configurations. These results highlight the importance of ANN architecture optimization in supporting early warning systems, agricultural planning, water resource management, and hydrometeorological disaster mitigation across Indonesia.

The Next-Gen Global Health 6.0 initiative offers an integrative model employing genomics, nano-immunotherapies, and artificial intelligence (AI) to address the escalating complexity of global health issues, particularly the convergence of infectious and chronic diseases. This framework advances precision medicine by integrating real-time genomic surveillance with AI algorithms, enabling timely prediction and response to outbreaks, as well as tailored therapeutic approaches. Nano-immunotherapies play a critical role in modulating immune responses with high specificity, especially in chronic infections and diseases resistant to conventional treatments. Through these synergistic technologies, the Next-Gen Global Health 6.0 approach aims to transcend traditional healthcare boundaries, offering scalable, data-driven interventions that are adaptable to varying resource levels worldwide. Emphasizing accessibility and equity, this framework highlights the necessity for innovative health policies and interdisciplinary collaboration to optimize deployment in underserved regions, ultimately contributing to sustainable, resilient healthcare systems prepared for evolving global health challenges.

The forecasting of advertisement tax payments at the Medan City Revenue Agency aims to support planning and decision-making regarding advertisement tax revenue from 2021 to 2023, covering the period from January to December. In this process, historical data on advertisement tax payments is analyzed to determine the most suitable ARIMA model by considering the Autoregressive (AR), Differencing (I), and Moving Average (MA) parameters. The research indicates that the ARIMA model can provide accurate predictions of advertisement tax payment trends, thereby serving as a tool to enhance the effectiveness of local tax management. For the period from January to October 2024, it is estimated that 1,141 individuals will make advertisement tax payments, with the lowest forecasted number occurring in January 2024 at 1,128 individuals.

This study aims to determine the forecasting of stock return volatility of energy companies listed on the Indonesian Sharia Stock Index (ISSI) using the ARCH/GARCH method. This study uses purposive sampling method and uses secondary data in the form of daily stock returns from January 2022 to June 2024 on 10 selected stocks. Data processing is done using Stata software. The results showed that of the 10 selected stocks, only 6 stocks, namely BYAN, ADRO, GEMS, PTBA, AKRA, and BSSR, were suitable for analysis using the ARCH/GARCH model. Meanwhile, PGAS, ITMG, PTRO, and HRUM do not show ARCH effect or do not contain heteroscedasticity. Statistical evaluation of volatility prediction shows that the selected models provide good predictions. Among the six stocks analyzed, ADRO, PTBA, and BSSR show high volatility, while BYAN, GEMS, and AKRA show low volatility. Therefore, investors should consider investment risk when evaluating stocks with different levels of volatility.

Estimating the effort, time, and cost needed to build a software project is an important task in software engineering. Estimating software prior to development can help to reduce risk and improve the project success rate. Researchers have developed numerous traditional and machine learning models to estimate software effort, but it has always been difficult to estimate effort precisely. This paper presents a predictive model based on artificial neural networks namely ANNs to predict the software effort. The NASA dataset is applied to construct the proposed model. The system was trained using 50 data points, and the remaining 10 were used for testing. It was concluded that the ANN approach could estimate the software effort with high accuracy. A comparative study with other published equations was also performed, and it was found that ANN had less error and produced better results than other existing methods.

The interest rate in the Iraqi economy represents an active and important element in the management of monetary policy in the Iraqi economy, as it is used by the monetary authority represented by the Central Bank of Iraq to influence the money supply, as well as the impact of this also by allocating the available resources for savings among foreign investments to achieve the central goal of the monetary authority of achieving stability in prices such as the interest rate and various prices and values of investments together and thus achieve balance at the economic and financial levels. This research analyzes the relationship between interest rate changes (IRC) and foreign direct investment (FDI) in the Iraqi economy during the period from (2004-2023). Multiple analytical tools were used, including descriptive statistics, correlation analysis, time series analysis, and prediction models using ARIMA and Prophet. The results showed an association between the two variables under consideration, with the ability of the ARIMA and Prophet models to provide accurate forecasts of future   FDI trends. A quantitative methodology that includes descriptive statistics, correlation analysis, time series models, and forecasting tools has been adopted to clarify the relationship between the two variables and draw conclusions that support economic decision-making.

Blasting is an activity that breaks rocks from their parent rock using explosives to create smaller fragments, making the loading and transportation processes easier. One of the environmental impacts of blasting activities is ground vibration. Ground vibration is one of the outcomes of blasting activities, and it is measured using the PPV (Peak Particle Velocity) value. Ground vibration can become a problem for companies if it exceeds the safe vibration quality standard (SNI 7571: 2010), as it can pose a danger to humans and nearby buildings. The Air Deck is an air column in the blast hole that aims to reduce energy vertically, this method can reduce the use of explosives. This research was conducted at the Sentuk Pit of PT. Multi Harapan Utama in East Kalimantan. Observations were made during 42 blast events to determine the impact of the air deck method on the resulting vibration. During the study, the maximum PPV value was 13.87 mm/s, while the minimum PPV value was 1.13 mm/s. The average ground vibration measurement value for non-air deck blasting was 4.40 mm/s, while the average ground vibration measurement value for air deck blasting was 3.95 mm/s. The use of this method also reduced the powder factor value. For non-air deck blasting, the average powder factor value was 0.26 kg/m³, and for air deck blasting, the powder factor value was 0.20 kg/m³, resulting in a 23.08% reduction in explosive usage. To calculate the predicted PPV, scaled distance calculations were used. Based on the predicted PPV calculation results, the deviation from the actual PPV was 1.59 mm/s.

This qualitative literature review explores the advances and challenges in predicting SME failures, focusing on methodological trends, data imbalance solutions, and model validation practices. Over recent years, machine learning techniques have gained prominence, replacing traditional statistical models and improving predictive accuracy. Key strategies for overcoming data imbalance, such as Synthetic Minority Over-sampling Technique (SMOTE) and cost-sensitive learning, have also been highlighted. However, challenges persist, particularly in model interpretability, generalization, and overfitting. The review emphasizes the need for continuous refinement of predictive models and validation practices to ensure real-world applicability. The findings suggest that while considerable progress has been made, future research should aim to enhance model transparency and address limitations in data representation to improve SME failure prediction across diverse contexts.

Forecasting the number of marriages is a prediction of marriages that will occur in the future based on current and past data.  The total population of the married population is continuous, that is, its growth continues without a break. The model used for continuous population is the logistic model. This study aims to see the growth of marriage in the period 2027 using the logistic model growth. Judging from the data obtained from BPS (Central Bureau of Statistics) of North Sumatra Province from 2020 to 2023, the capacity limit (C) =  . The logistic model that can be used to parameterize the marriage rate in North Sumatra province is with a value of k = -0.25019918023 with the formula  .Based on the logistic model, the predicted marriage rate in North Sumatra province for 2027 is 64305.93339.

Abstract. From the perspective of Micro, Small, and Medium Enterprises (MSMEs), fluctuations in raw material prices are highly concerning as they can significantly impact business stability. While MSMEs may tolerate price fluctuations to some extent, from an industrial engineering perspective, such a passive approach contradicts the principles of continuous improvement. This study seeks to predict the price of large red chili peppers using five regression models implemented through Orange Data Mining: Linear Regression, Support Vector Machine, Decision Tree, k-Nearest Neighbors (kNN), and Gradient Boosting. Due to the limited availability of daily data, particularly within a daily timeframe, the study utilized weekly data spanning three years. The results of the Test and Score evaluation shows Gradient Boosting as the best-performing model, achieving a Mean Absolute Percentage Error (MAPE) of 0.7%. However, the MAPE for predictions in January 2025 increased to 15.8%. This error is expected to decrease as more weekly data becomes available to mitigate the inaccuracies inherent in this model. Keywords: prediction, red chilli, regression, supervised learning , orange data mining. Abstrak. Dalam perspektif UMKM, fluktuasi harga bahan baku adalah suatu hal yang paling ditakuti karena berakibat pada ketahanan usaha yang menjadi tidak menentu. Pada suatu kondisi, fluktuasi harga dapat diterima para UMKM, namun dalam perspektif teknik industri, sikap UMKM tersebut tidak sesuai prinsip continuous improvement. Penelitian ini mencoba untuk memprediksi harga cabai merah besar dengan menggunakan 5 model regresi dibantu Orange Data Mining. Yaitu Linear Regression, Support Vector Machine, Tree, kNN, Gradient Boosting. Data yang diperlukan sebagian besar tidak tersedia, khususnya dalam kerangka waktu harian sehingga penelitian ini menggunakan data mingguan selama 3 tahun. Hasil Test and Score menunjukkan model Gradient Boost terpilih menjadi model terbaik dengan tingkat MAPE 0.7% namun MAPE pada tahap Prediction di bulan Januari 2025 menjadi 15.8%. Error tersebut akan berkurang ketika data mingguan sudah cukup banyak untuk menambal kesalahan yang dihasilkan model ini Kata kunci: prediksi, cabai merah, regression, supervised learning , orange data mining.

Fraud in digital transactions has become a serious issue threatening the security and integrity of the fintech and e-commerce sectors. To address this problem, machine learning technology has emerged as an effective solution for automatically detecting anomalies and fraudulent transactions. This study aims to analyze the application of machine learning algorithms, specifically Support Vector Machine (SVM), Random Forest, and Ensemble Learning, in detecting fraud in digital transactions. The research adopts a quantitative approach with experimentation, testing the effectiveness of the three algorithms using a digital transaction dataset consisting of both fraudulent and non-fraudulent transactions. The results show that the Random Forest algorithm performs the best in terms of accuracy and recall, followed by Ensemble Learning, which enhances fraud detection performance by combining multiple prediction models. Meanwhile, SVM demonstrates satisfactory performance but is prone to overfitting issues when handling large and complex datasets. The study also finds that the problem of imbalanced data can affect model accuracy, and data balancing techniques such as oversampling are required to improve fraud detection performance. Overall, the findings suggest that machine learning, particularly Random Forest and Ensemble Learning algorithms, can be relied upon to improve fraud detection in digital transactions. However, challenges such as model interpretability and the need for periodic algorithm updates still need to be addressed to enhance the effectiveness of fraud prevention systems in countering the ever-evolving nature of fraud.

The rapid advancement of digital technology, particularly Artificial Intelligence (AI), has reshaped various sectors, including the field of law. This study aims to examine the integration of AI in law firms’ operations, focusing on its potential benefits, legal challenges, and ethical implications in the Indonesian legal context. This research employs a qualitative approach through a normative juridical method, supported by literature review and case analysis related to the use of AI in legal practice. Relevant legislation, including Law No. 11 of 2008 on Electronic Information and Transactions, is analyzed to assess the existing regulatory framework. The study reveals that while AI enhances efficiency in tasks such as document analysis, case prediction, and legal drafting, it also raises concerns about algorithm reliability, data bias, and the absence of specific AI-related legal regulations in Indonesia. Law firms must ensure transparency, accountability, and ethical responsibility when adopting AI to align with the principles of justice. Human interaction remains crucial to maintain trust and professional integrity in client services. The research contributes to the ongoing discourse on developing legal and ethical frameworks for AI implementation in the legal sector. It suggests the need for comprehensive regulation and professional guidelines to optimize AI utilization while safeguarding justice and ethical standards. The study is intended for publication in a national academic journal.

Companies often face various obstacles related to managing raw material inventory to meet demand, one of which is Peuyeum Ketan Istimewa. Working in the food processing industry, of course, raw material inventory management needs to be planned optimally to avoid various risks that can harm the company. The Quantity Discount model is used to take advantage of cost savings provided by suppliers when purchases are made in large quantities, while other efforts that can help manage raw materials in a company are by knowing the safety stock and reorder point of raw materials and also forecasting demand to predict future demand. This study will use the Quantity Discount model which optimizes inventory levels by considering storage costs, ordering costs, and quantity discounts. The calculations carried out are also to find the value of the company's Safety Stock and Reorder Point. The results of this study indicate that the use of the Quantity Discount method can reduce total costs by Rp26,319,267/year, while forecasting using the seasonality method increases the accuracy of demand predictions, thus enabling more efficient inventory management. The implementation of this model is expected to provide a significant contribution to operational efficiency and cost reduction at Peuyeum Ketan Istimewa

This study explores the application of machine learning to predict students' GPA based on behavioral and time-related factors, including study hours, extracurricular activities, sleep, social interactions, and physical activity. Seven regression algorithms were employed to evaluate predictive accuracy using metrics such as MAE, RMSE, and R2 Among these, Regularized Linear Regression demonstrated the highest accuracy and interpretability, highlighting its suitability for this dataset. The findings emphasize the potential of machine learning in identifying key predictors of academic performance and offer practical applications for personalized academic advising and time management. This research provides a data-driven framework to support students and educators in optimizing learning outcomes.

Bioinformatics can help identify cancer risk factors, predict cancer, and develop effective prevention strategies. The development of bioinformatics technologies such as genetic data analysis, development of prediction models, and personalization of treatment have opened up new opportunities in cancer prevention. This research aims to examine the role of bioinformatics in preventing cancer and building a better health future. By understanding the potential of bioinformatics, we can develop effective prevention strategies and improve people's quality of life. Prevention and efforts to control breast cancer were discovered using bioinformatics technology. This research shows that the implementation of bioinformatics has a positive impact on efforts to prevent breast cancer for the future of health.

Hydroponic plant cultivation is booming, but stock and sales are hard to predict. Poor prediction can cause farmers to overstock and lose money. This study suggests a framework that uses several machine learning models, including Linear Regression (LR), Random Forest (RF), Decision Tree (DT), and Extreme Gradient Boosting. "Ensemble Learning," which combines these models, should yield more accurate and generalizable results than a single model. This framework is assessed using historical hydroponic plant sales data and related factors like price, weather, and market trends. The model's performance is measured by the difference between predictions and actual values using RMSE and MAE metrics. This framework should improve hydroponic plant stock and sales predictions. Farmers can make better production, inventory, and harvest distribution decisions. Besides reducing financial losses, this reduces food waste and improves food security.

Operations management is a series of activities related to planning, organizing, controlling and supervising all resources used in the process of producing goods or services. The main function of operations management is to create quality products or services, at efficient costs, at the right time, and in accordance with market demand. This research is quantitative research that works with numbers and the data is in the form of numbers which are then analyzed using statistics to test hypotheses or to answer specific research questions and to make predictions. This research approach is explanatory research where data collection is carried out simultaneously in one stage (one shot study} or in a cross-section through a questionnaire. One of the main impacts of operations management what is good is increasing the efficiency of the production process by designing and managing efficient production processes, companies can optimize the use of available resources, reduce waste, and increase output without increasing significant costs. Effective operations management has a significant impact on various aspects of company performance, including operational efficiency, cost control, product quality and service, and customer satisfaction. By implementing good operations management principles, companies can increase their competitiveness, reduce waste, and improve the customer experience.

Technological advancements have brought significant transformations across various fields, including the application of machine learning in recommendation and classification systems. Machine learning leverages data processing, utilizes algorithms, and efficiently identifies patterns to produce accurate recommendations and predictions. This study aims to review machine learning-based recommendation system approaches, analyze model performance, and compare the algorithms used. A literature review was conducted by examining journals published in the past five years, focusing on algorithm implementation. The findings indicate that the Naïve Bayes algorithm delivers the best performance, achieving an accuracy of up to 97%. This algorithm is particularly well-suited for processing small to medium-sized datasets with high efficiency. The research provides comprehensive insights into the performance and limitations of various algorithms, serving as a valuable guide for future developments in the field.

In the increasingly competitive Industry 4.0 era, companies need to forecast product demand to meet consumer needs and improve operational efficiency. CV Mamifood Sukses Abadi, an MSME that produces milk and cheese-based foods, has faced sales fluctuations in the last two years, thus requiring accurate forecasting to plan production strategies and resource management. This research aims to forecast demand using the Fuzzy Mamdani method and the POM-QM application. Fuzzy Mamdani was chosen for its ability to handle decision-making with multiple criteria and balanced weights, while POM-QM was used to validate predictions through quantitative methods. Product sales data for the years 2022 and 2023 were analyzed to produce accurate forecasts. The methods used include Moving Average for forecasting and evaluation of the results using MAPE. The analysis results show that the Moving Average method with N = 2 produces a MAD value of 402.523 and a MAPE of 22.155%, while the results of Fuzzy Mamdani show that product demand in the next period tends to decrease. This research is expected to provide insight for CV Mamifood Sukses Abadi in planning a more efficient production strategy.

In recent decades, artificial intelligence (AI) has significantly advanced and shown great potential across various fields, including bioinformatics. This paper examines current trends in AI applications within bioinformatics, highlighting future potentials and the challenges of integrating these technologies. The research utilizes secondary data collection from scientific literature, books, conference reports, and official documents on AI and bioinformatics, sourced from reputable databases like Scopus, IEEE, PubMed, and Google Scholar. Through comparative analysis, similarities, differences, and technological advancements were identified and discussed. Descriptive narrative interpretation was employed to provide a holistic view of AI trends and potential in bioinformatics. Key findings indicate that AI, particularly machine learning and deep learning, is instrumental in genomic data analysis, protein structure prediction, drug discovery, and clinical bioinformatics. Furthermore, the study underscores the benefits of AI in enhancing data analysis accuracy and efficiency, while addressing ethical and technical challenges. Future prospects emphasize the importance of interdisciplinary collaboration to fully leverage AI's capabilities in bioinformatics.