METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi

Analisis Multi-Kriteria dengan Pendekatan Analytical Hierarchy Process untuk Strategi Mitigasi dan Adaptasi Bencana Banjir di Distrik Nabire Kabupaten Nabire

2025-12-02T22:24:09+07:00

Nabire Regency, Central Papua Province, has a high vulnerability to flooding due to significant rainfall intensity with type 1 Local Seasonal Zone, which only has one season throughout the year, namely the Year-Round Rainfall (HST) type, with an average rainfall of more than 300 mm per month, ranging from 344 mm to 522 mm per month. Risk analysis was conducted using the Analytical Hierarchy Process (AHP) method to determine the priority of factors causing flooding, including hydrological aspects, land use, infrastructure, and socio-economic impacts in a systematic manner. The results of this study indicate that the analysis of public perception of flooding disasters was conducted by modeling data using a Likert scale, which was processed computationally to generate patterns of public perception. The Analytical Hierarchy Process (AHP) method was used to determine the priority of data-based mitigation strategies. The results confirm that BPBD plays a dominant role in flood risk management through the integration of adaptive and sustainable environmental information systems.

Perancangan Smart Stick untuk Mobilitas Penyandang Tunanetra Berbasis Mikrokontroler

2025-04-21T15:22:17+07:00

The development of assistive technology for visually impaired individuals is essential to enhance their mobility and safety. This research successfully designed and developed a Smart Stick based on a microcontroller, equipped with ultrasonic and water level sensors to detect obstacles and water puddles in real-time. The system provides immediate warnings through a speaker, allowing users to navigate their environment more effectively. The testing phase demonstrated that the ultrasonic sensor accurately detects obstacles within a range of 50–150 cm, while the water level sensor activates an alarm when the water reaches 40 mm. The results indicate that the Smart Stick is reliable in detecting obstacles and providing early warnings, improving the independence and security of visually impaired users. Future improvements may include IoT integration, Bluetooth headset compatibility, and enhanced sensor accuracy to optimize its functionality.

Business Intellegenge untuk Perencanaan Strategi Pemasaran pada UMKM Sarung dengan Manajemen Dashboard

2025-12-02T13:56:04+07:00

MSMEs are the backbone of the national economy, the government is trying to recover the economy after the Covid-19 pandemic by making a new breakthrough with digitalization. Digitalization helps MSMEs to process and analyze data for decision making. The data stored in the company is increasing, so it requires Business Intelligence to make it easier for companies to present information. MSME Abitex experienced problems in planning sales strategies by looking at interest in each city. The stages of research carried out were problem identification, data collection, design, manufacture, testing results. In identifying problems, problems were found in monitoring sales to create sales strategies, in data collection from 2021 to 2023. The number of transactions was 807 sales with 3 types of sarongs, a total of 14 sarongs produced. In designing using a star schema obtained from the sales fact table, time dim, customer dim, goods dim. Business intelligence can display data visualization by grouping by product, customer and by time, and can see interest in products in each city

Efisiensi Pemesanan Makanan dengan Aplikasi Android Berbasis Metode Rapid Application Development

2025-07-07T17:24:57+07:00

Technological advancements offer efficient solutions for handling various activities, including those in the culinary business sector. Along with the increasing use of smartphones, particularly those running the Android operating system, there is a growing demand for practical and fast food ordering systems. This study aims to design and develop an Android-based food delivery application to address the limitations of manual ordering methods in restaurants, such as recording errors and long queues. The method used is Rapid Application Development (RAD), which includes several stages such as business modeling, data modeling, and application generation. Data collection techniques include observation, interviews, and literature review, with qualitative analysis. The implementation results show that the “PESANMAKAN” application can accelerate the ordering process, display complete menu information, and provide order tracking and transaction history features. Testing using the black-box method confirms that all application functions work as expected. This study also supports the achievement of novelty by producing an integrated system that includes ordering, payment, and order tracking features based on an actual case study in the field. In conclusion, the application effectively improves restaurant operational efficiency and customer satisfaction and serves as a relevant digital solution for modern food ordering needs.

Analisis Manajemen Risiko Aset Teknologi Informasi pada Perusahaan Sistem Integrator dengan Menggunakan Metode Octave Allegro

2025-12-02T14:52:45+07:00

The utilization of information technology frequently carries significant security risks, both from external threats such as cyberattacks (viruses, malware, phishing, ransomware) and from internal factors such as human error. This research aims to identify, assess, and mitigate the risks of information technology assets in an Indonesian system integrator company using the OCTAVE Allegro method. This method was chosen because it focuses on critical information assets and provides a structured approach through eight steps in four phases of analysis. The results of the study show that there are four critical assets in the company's information technology, namely hardware, software, data and information, as well as access rights and credentials. Based on the risk assessment matrix, data and information assets have the highest risk score with an average of 38.8, followed by access rights and credentials (38), software (37.42), and hardware (36.33). All risk categories are in POOL 1, which means they require immediate mitigation measures. Consistent implementation of risk management is expected to strengthen the company's resilience to information security threats and also enhance its reputation and competitiveness in the technology industry.

Analisis Pengaruh Variasi Nilai P Pada Metode Minkowski Distance dalam Menentukan Kemiripan Abstrak Skripsi

2025-05-09T20:40:30+07:00

The Computer Science Study Program of Universitas Methodist Indonesia is faced with the challenge of verifying the authenticity of student theses, which is still done manually. This study applies the Minkowski Distance method to analyze the level of similarity of thesis abstracts using one hundred samples. The preprocessing stage is carried out through five systematic steps: cleansing to remove non-alphabetic characters, case folding for letter standardization, tokenizing for text splitting, filtering for stopword elimination, and stemming to obtain root words, resulting in word vectors that are analyzed. The Minkowski Distance method is implemented with three parameter variations, P = 3, P = 5, and P = 7, where the selection of parameters is based on differences in sensitivity to vector dimensions; the higher the P value, the greater the emphasis on significant differences between dimensions. The test results show that the parameter P = 7 provides the most optimal similarity measurement with the smallest distance of 3.84 for documents with the highest similarity. These findings contribute to the development of a more effective similarity detection system to maintain academic integrity.

Perancangan E-Sukerti (Surat Keterangan Elektronik) Desa Baturiti Berbasis Web Berbasis Black Box Testing

2025-05-19T11:02:37+07:00

The digital transformation of village administration is a strategic step in enhancing the efficiency and transparency of public services. This study aims to design and develop the E-SUKERTI (Electronic Certificate) system for Baturiti Village, a web-based platform to facilitate the creation and management of electronic certificates. The system development follows a web-based system design approach, with system testing conducted using the Black Box Testing method. Testing was performed with 16 test cases focusing on system functionality to ensure compliance with user requirements. The results indicate that all system features function correctly, achieving a 100% success rate, demonstrating that the system meets its functional requirements. The implementation of E-SUKERTI is expected to improve the speed, accuracy, and transparency of village administrative services for the community.

Perbandingan Convolutional Neural Network dan Algoritma Machine Learning Konvensional untuk Klasifikasi Kemiskinan Multidimensional di Indonesia

2025-12-02T15:13:11+07:00

Multidimensional poverty in Indonesia is a complex phenomenon involving various interconnected social, economic, and structural aspects. Conventional approaches to poverty classification often fail to capture non-linear interaction patterns and spatial dependencies inherent in multidimensional socio-economic data. This research aims to compare the performance of Convolutional Neural Networks (CNN) with conventional machine learning algorithms such as Random Forest and XGBoost in classifying multidimensional poverty in Indonesia. The research method employs a comparative quantitative approach using data from the 2023 National Socio-Economic Survey (Susenas) by BPS, covering 8,000 household observations. The target variable is multidimensional poverty status based on the Multidimensional Poverty Index (MPI) with a 1/3 cutoff. Data was split 70:30 for training and testing, with preprocessing including missing value imputation, one-hot encoding, and Min-Max scaler normalization. The CNN model was designed with a two-convolutional-layer architecture, while Random Forest used 200 decision trees and XGBoost with 200 estimators. Research results demonstrate that CNN provides the best performance with 82.4% accuracy, outperforming Random Forest (80.1%) and XGBoost (81.2%). Important variable analysis reveals that housing infrastructure conditions, household head education level, and sanitation access are key factors in determining multidimensional poverty, providing strategic input for formulating more targeted poverty alleviation policies.

Analisis Sentimen Orang Tua Murid Baru Terhadap SMPN 40 Samarinda pada SPMB 2025 Menggunakan Algoritma Naïve Bayes

2025-12-02T11:47:44+07:00

The New Student Admission Selection (SPMB) plays an essential role in ensuring equal educational access in Indonesia. However, during SPMB 2025 at SMPN 40 Samarinda, many candidates living nearby did not choose the school as their first preference, suggesting that perceptions and school image significantly influenced their choices. This study aims to analyze new student parents' sentiments toward SMPN 40 Samarinda using the Naïve Bayes algorithm combined with the Term Frequency–Inverse Document Frequency (TF-IDF) technique. Data were collected from 42 respondents and categorized into positive, neutral, and negative sentiments. The model achieved an accuracy of 86%, a precision of 56%, and a recall of 63%, showing that Naïve Bayes performs effectively on limited data, though it is less sensitive to minority classes. The analysis revealed that most parents expressed positive perceptions, indicating growing trust that SMPN 40 Samarinda can support students’ character development. These findings emphasize the importance of strengthening school image and service quality while highlighting the potential of machine learning–based sentiment analysis as a data-driven approach to understanding educational perceptions.

Klasifikasi Pola Konsumsi Energi Rumah Tangga Menggunakan Algoritma Machine Learning untuk Mendukung Implementasi Smart City

2025-12-02T22:32:00+07:00

Population growth in urban areas drives a significant increase in household energy consumption. This condition poses a major challenge for the implementation of the smart city concept, particularly in achieving energy efficiency and sustainability. This study aims to classify household energy consumption patterns based on household power consumption data to support intelligent decision-making in urban energy management. The research method includes data preprocessing, data cleaning, and aggregation of daily energy consumption by utilizing key attributes such as Global Active Power, Voltage, Global Intensity, and three sub-metering variables. Consumption pattern categories are formed using the tertile method into three classes: Low, Medium, and High. Several machine learning algorithms are applied to build the classification model, including Logistic Regression, K-Nearest Neighbors (KNN), Random Forest, and Gradient Boosting. The test results show that the Random Forest model with hyperparameter adjustments produces the best performance with an accuracy value of 0.98 and an F1-macro value of 0.98, surpassing other models. These findings indicate that the ensemble learning approach is able to capture the complexity of household energy consumption patterns more effectively than conventional linear models. The contribution of this research lies in the development of a machine learning-based predictive model to support adaptive energy consumption monitoring and control systems in smart city implementations.

Penerapan Algoritma K-Nearest Neighbors dalam Mengklasifikasi Penyakit Multiple Sclerosis

2025-12-04T12:07:03+07:00

The central nervous system is impacted by multiple sclerosis (MS), a chronic autoimmune disease that requires early identification for successful treatment. Because of its many symptoms and similarities to other neurological disorders, MS can be difficult to diagnose. Artificial intelligence techniques like the K-Nearest Neighbors (KNN) algorithm can be used to help with quicker and more precise classification in order to solve this problem. The goal of this study is to classify MS using the KNN technique and assess how well it performs in this regard. The Kaggle platform provided the dataset, which consists of 273 patient records with 18 clinical characteristics. With k = 3 as the number of neighbors, the data was split into 80% for training and 20% for testing. The Python programming language was used to implement the classification procedure. According to the findings, the KNN algorithm classified MS with an accuracy of 81.82%. The precision, recall, and f1-score for class 1 were 0.83, 0.76, and 0.79, respectively, according to additional analysis utilizing a classification report, whereas the scores for class 2 were 0.81, 0.87, and 0.84. These findings suggest that the KNN method has the potential to serve as a supportive tool in the diagnosis of Multiple Sclerosis.

Penerapan Algoritma Decision Tree C4.5 Pada Test MBTI Berbasis Web

2025-10-01T22:22:53+07:00

A major problem in student personality assessment is the manual process of completing and interpreting test results, which leads to subjective bias and delays in counseling services. To address this, this study applies the Decision Tree C4.5 algorithm to a web-based MBTI test to produce an objective and efficient personality type classification. This study discusses the implementation of the Decision Tree C4.5 algorithm in a web-based Myers-Briggs Type Indicator (MBTI) test to classify students’ personality types at Musi Charitas Catholic University. The research objectives are (1) to apply and evaluate the Decision Tree C4.5 algorithm in personality classification based on MBTI test results, and (2) to develop a counseling support system capable of providing automatic, objective, and easy-to-understand classification results. The research method employed is development research (Research and Development) using the Waterfall model, including requirement analysis, system design, implementation, testing, and evaluation. The C4.5 algorithm was implemented to construct a classification model based on decision rules, which was then integrated into the web application. System testing using Black-Box and White-Box methods ensured that the system operates according to specifications and that all logical paths have been tested. Evaluation results indicate a classification accuracy of approximately 86% with consistent precision, recall, and F1-score values, demonstrating the effectiveness of the C4.5 algorithm in personality type classification. The system improves efficiency, accessibility, and objectivity in personality assessment compared to manual methods and can support sustainable student counseling and development services.