E-Journal Politeknik Negeri Cilacap
Not a member yet
919 research outputs found
Sort by
Analisis Intensitas Turbulensi Terhadap Kestabilan Kecepatan Angin Test Section pada Struktur Wind Tunnel
Get PDFWind tunnels in aerodynamic testing always have very large sizes to avoid high turbulence intensity. Turbulence intensity analysis is used to determine the size of a smaller wind tunnel to be more efficient in limited space. The use of epoxy fiber resin material is because lighter than aluminum with a thickness of 5mm. The purpose of the study was to produce a wind tunnel with a small size with low turbulence intensity and minimize large manufacture costs. The method used is constructive to analyze the wind tunnel design in determining the maximum wind flow speed at test section does not exceed the turbulence intensity limit. The results of the analysis showed that the wind tunnel structure design has the ability to receive an inlet wind flow of 5 m / s with a maximum wind flow speed at the test location of 10.7 m / s. The wind tunnel design cannot exceed the maximum wind flow speed at the test section because it will produce turbulence intensity above 5% which affects the test result
Perbandingan Random Forest dan K-Nearest Neighbors untuk Klasifikasi Body Mass Index Menggunakan SMOTE-ENN untuk Mengatasi Ketidakseimbangan Data pada Analisis Kesehatan
Get PDFThis study aims to compare the Random Forest and K-Nearest Neighbors (KNN) algorithms in Body Mass Index (BMI) classification using the SMOTE-ENN method to address data imbalance. The dataset consists of 2111 entries with demographic and health attributes of individuals. Data imbalance poses a significant challenge that may affect the accuracy of machine learning models. The SMOTE-ENN combination was employed to improve data distribution, enabling models to recognize patterns in minority classes better. Key evaluation factors included both algorithms\u27 accuracy, precision, recall, and F1-score. Results indicate that the Random Forest algorithm achieved higher performance with 100% accuracy than KNN with 96% after applying SMOTE-ENN. These findings highlight the unique contribution of SMOTE-ENN in handling imbalanced data, enhancing classification model quality, and significantly impacting machine learning applications in healthcare.
 
Evaluasi dan Strategi Biodiesel Sebagai Energi Terbarukan di Indonesia: Literature Review
Get PDFBiodiesel memiliki potensi besar sebagai energi terbarukan untuk mengurangi ketergantungan Indonesia pada bahan bakar fosil sekaligus menekan emisi gas rumah kaca. Penelitian ini bertujuan mengevaluasi potensi biodiesel di Indonesia melalui kajian literatur terhadap kebijakan, kendala, serta strategi pengembangannya. Metode yang digunakan adalah literature review dengan menelaah 23 artikel terbitan 2015–2025 yang relevan dengan topik biodiesel. Hasil kajian menunjukkan bahwa meskipun kebijakan mandatori B-2,5 hingga B-35 berhasil meningkatkan produksi dan konsumsi biodiesel secara signifikan, implementasinya masih menghadapi empat kendala utama, yaitu ketergantungan pada kelapa sawit sebagai bahan baku, keterbatasan infrastruktur distribusi, hambatan pendanaan akibat biaya produksi tinggi, serta kompleksitas teknologi konversi. Strategi yang diusulkan meliputi diversifikasi bahan baku melalui minyak jelantah, limbah pertanian, dan mikroalga; pengembangan teknologi katalis heterogen dan metode intensifikasi proses (microwave, ultrasonik); optimalisasi subsidi dan instrumen fiskal; pembangunan infrastruktur distribusi di luar Jawa; serta kolaborasi internasional dalam transfer teknologi dan pasar ekspor. Kajian ini menegaskan bahwa dengan integrasi strategi tersebut, biodiesel berpotensi menjadi pilar utama transisi energi berkelanjutan di Indonesia.
Kata kunci: Kajian Literatur, Kebijakan Biodiesel di Indonesia, Solusi Energi Keberlanjutan
Fuzzy Expert System for Decission Support to Diagnosis Leukemia
No full textLeukemia is a cancer of the blood and bone marrow. In leukemia, the bone marrow produces too many abnormal white blood cells. These abnormal cells cannot fight infections well and can displace healthy blood cells, which can cause anemia and bleeding. In this study, a fuzzy method will be implemented to diagnose leukemia and the results will later be compared with expert diagnoses. Fuzzy logic was chosen because it allows for degrees of truth between 0 (completely false) and 1 (completely true) and it is suitable for situations where human expertise relies on experience and judgment rather than fixed rules. Fuzzy systems can analyze large amounts of data quickly, thereby accelerating the diagnosis and decision-making process, especially when used in medical decision support systems. This study produced a leukemia diagnosis accuracy of 88.83% when compared with the results of expert diagnoses using the same symptom and sample data
Addressing Insider Threats: The Human Factor in Cybersecurity for Financial Institutions
Get PDFFinancial institutions face persistent cybersecurity threats, with insider threats emerging as a particularly complex challenge due to their human-centric nature. This study aims to examine the human factor in cybersecurity within financial institutions, with a focus on insider threats and strategies to mitigate them. A hybrid research approach was used, combining a systematic literature review (SLR) and qualitative case study analysis to investigate cybersecurity risks, AI-driven solutions, and regulatory compliance. The findings reveal that AI-powered tools—such as behavioral biometrics, machine learning, and blockchain technologies—substantially enhance fraud detection and risk management. Real-world implementations in financial institutions demonstrated improved threat response, reduced regulatory penalties, and increased operational efficiency. The study concludes that integrating technological tools with a strong cybersecurity culture can significantly mitigate insider threats
Evaluating ERD Models and RAID-Based Storage for Query Performance Optimization in Relational Databases
Get PDFThe amount of data stored in magnetic disks (e.g., floppy disks) increases by 100% each year for each department in a company, necessitating efforts to maintain an optimal database system. Designing a database is the initial step in creating a system with optimal performance. However, database design alone is not sufficient to enhance performance. One approach to improving data transaction speed is by optimizing query processing. This research evaluates different relational database models using varying amounts of data. Query costs are analyzed using the Cost-Based Optimizer method and access time measurements. The results of this study provide insights for database administrators in designing relational database models effectively and selecting appropriate query structures to optimize database performance. The findings indicate that: (1) database design can be optimized by separating entities based on specialized usage, and (2) factors such as record count, attribute size, query type, use of unique or primary keys, order-by clauses, index sequences, and SQL function usage significantly impact query cost and overall performance
Optimisation of Criminal Data Clustering Model using Information Gain
Get PDFCrime is a phenomenon that significantly impacts society, necessitating mapping efforts that can be utilized for further analysis. Clustering, as a data analysis technique, groups objects based on similarities or differences in their characteristics. This approach enhances the understanding of data by identifying patterns and relationships between criminal events, such as crime type, time, and location. By clustering crime data based on similar characteristics, authorities can make more effective and efficient decisions in crime prevention and control. However, selecting too many attributes can negatively affect clustering performance. To address this issue, this study applies Information Gain reduction to reduce data dimensionality by eliminating attributes with low informational contribution. Additionally, three clustering methods K-Medoid, K-Means, and X-Means are compared to evaluate their performance. The concept of Information Gain is also integrated to optimize cluster formation, measuring how much an attribute contributes to distinguishing objects within a cluster. By leveraging Information Gain, this study aims to identify the most relevant and influential attributes in forming clusters that accurately represent crime data characteristics. Furthermore, the number of clusters generated is evaluated using the Davies-Bouldin Index (DBI). The results indicate that the K-Means algorithm outperforms the other two methods, achieving the best clustering quality with an optimal number of clusters (k = 6) and the lowest DBI value
Analisis Proses Preventive Maintenance pada Pump Tank Farm PT. H dengan Metode Fuzzy Failure Mode and Effect Analysis (FMEA) di PT. M
Get PDFPT.M with PT. H in the preventive maintenance process of the pump tank farm unit. Before the maintenance process is carried out, an analysis is carried out to determine the priority and scale of potential failures that occur in the pump unit at PT. H. The main purpose of preventive maintenance is to ensure all machinery and equipment are functioning properly and improve their reliability. This analysis is carried out as an action to eliminate or reduce the risk of danger, especially for the highest risk priority, before carrying out preventive maintenance. The analysis method used is the fuzzy logic FMEA method through simplification with the Three Triangular Fuzzy Number method. Based on the results of the fuzzy RPN calculation in the table above, there are seven pumps that are prioritized for preventive maintenance actions. The seven pumps are UP-AT-01A, UP-AT-01B, TP-AT-01A, TP-AT-01B, TP-AT-06A, TP-AT-04A and UP AT-03B
Integrated Mechanized System of Agro-Aquaculture System: Sustainable Farming Model for Poultry, Catfish, and Small Scale Farm.
Get PDFOne of the major factors that makes up a developed country is the ability to feed themselves, which agricultural system of a country needs to be enhanced to achieve such standard. This research presents the design and development of a mechanized integrated farming system, uniting poultry, fishpond, and small scale corn plantation. The methodology of this research includes conceptual design and principle of operation of the intended design, application mathematical models and machine design principles to determine the required dimensions of the machine structural parts, conveyor components, and solar energy, then material selection and assembly of the entire mechanism. Afterward, the developed machine was used to rear chicken, fish and small scale corn plantation as well as traditional means and cost comparison of the two methods were conducted. From the result obtained, a chicken prototype farm with 125 cm x 35 cm x 40 cm dimension comfortable enough to house 5 chicken and fish, and a solar energy of 750 W which conveys chicken droppings on speed of 0.0679 m/s was established. Furthermore, the comparative cost analysis shows that integrated farming reduces poultry and catfish feed costs by 20% and 40%, respectively, while surpassing traditional farming in savings and profitability by over 200%. The mechanized integrated farming system presented a sustainable and resource-efficient model, maximizing waste utilization, reducing environmental impact, and promoting ecological balance. This research contributes to evolving agricultural practices, offering insights for diverse farming systems
Estimasi Posisi untuk Nagivasi Local Menggunakan Gated Recurrent Unit (GRU)-Based IMU Denoising dan Extended Kalman Filter pada Robot Terapung Greeniebot
Get PDFRobot terapung Greeniebot memanfaatkan sensor IMU MPU6050 sebagai sumber utama untuk mengestimasi posisi pada lintasan lurus di area pertanian bawang. Namun, IMU low-cost memiliki noise tinggi, bias, serta drift integrasi yang menyebabkan akurasi estimasi posisi menurun. Penelitian ini mengusulkan kombinasi Gated Recurrent Unit (GRU) sebagai learned denoiser dan Extended Kalman Filter (EKF) untuk meningkatkan kualitas estimasi posisi. Pengujian dilakukan pada lintasan maju 2 meter dan kembali ke titik awal, masing-masing sebanyak lima kali run. Hasil menunjukkan bahwa pra-pemrosesan awal mampu mereduksi noise IMU sebesar 36–41%, sedangkan GRU-denoising meningkatkan reduksi noise hingga 62–68% pada kanal akselerometer dan giroskop. Pada estimasi posisi maju (0 menuju 2 m), metode tanpa GRU menghasilkan error rata-rata 0.33 m, sedangkan metode GRU+EKF menurunkannya menjadi 0.08 m atau meningkat 76%. Pada lintasan mundur (2 menuju 0 m), error rata-rata turun dari 0.07 m menjadi 0.02 m setelah penerapan GRU+EKF. Grafik lintasan memperlihatkan bahwa metode tanpa GRU menghasilkan penyimpangan Y hingga 0.3–0.35 m, sedangkan GRU+EKF mampu menjaga lintasan tetap rapat, halus, dan mendekati garis ideal. Hasil penelitian menegaskan bahwa integrasi GRU-denoising dan EKF secara signifikan meningkatkan stabilitas sinyal IMU dan akurasi estimasi posisi robot terapung