E-Journal Politeknik Negeri Cilacap
Not a member yet
919 research outputs found
Sort by
Improved Malnutrition Classification in Toddlers Using Mutual Information-Guided Feature Selection and Hybrid KNN–MLP Ensemble Learning
Full text linkMalnutrition remains a significant public health challenge in Indonesia, with early detection being crucial for effective intervention. Previous studies utilizing the K-Nearest Neighbor (KNN) algorithm demonstrated promising results in classifying malnourished toddlers based on anthropometric data. However, single-model approaches often suffer from sensitivity to noise and limited generalization. This study proposes a hybrid ensemble model combining KNN and Multi-Layer Perceptron (MLP), integrated with mutual information-based feature selection, to improve classification performance. Using a dataset from Puskesmas Ubung, Bali, comprising 1,319 records with nine anthropometric features and a binary malnutrition label, the model was evaluated under stratified five-fold cross-validation. The proposed KNN–MLP ensemble with top-ranked features achieved 94.3% accuracy, surpassing both standalone KNN and MLP models. Additional metrics, including precision (91.7%), recall (89.4%), F1-score (90.5%), and MAE (0.05), confirmed the model\u27s robustness and reliability. These findings demonstrate that ensemble learning combined with feature selection significantly improves early-stage malnutrition classification, offering a scalable approach for decision-support systems in public health interventions
Analisis Kinerja Proteksi Feeder CLWU Gardu Induk Garut Saat Kondisi Eksisting Dan Manuver Jaringan
Full text linkPenelitian ini mengkaji seberapa baik fungsi sistem proteksi pada penyulang CLWU dan MGWT di Garut 150 kV yang dioperasikan oleh PT PLN (Persero), pada dua skenario utama kondisi eksisting dan manuver jaringan. Tujuan utamanya adalah untuk menilai seberapa baik relai proteksi Over Current Relay (OCR) dan Ground Fault Relay (GFR) bereaksi terhadap berbagai jenis masalah hubung singkat, termasuk gangguan satu fasa ke tanah, dua fasa, dua fasa ke tanah, dan gangguan tiga fasa. imulasi dilakukan menggunakan perangkat lunak ETAP 19.0.1 dengan skenario pembebanan minimum 20%, 80%, dan 100%. Hasil simulasi menunjukkan adanya ketidakefisienan pada pengaturan waktu kerja relay, di mana sebagian besar relay beroperasi lebih dari batas waktu standar (<1 detik), serta ditemukan miss coordination antara relay LV dan HV pada beberapa titik. Penelitian ini menekankan perlunya evaluasi ulang dan optimasi pengaturan sistem proteksi agar kontinuitas dan keandalan sistem distribusi tenaga listrik 20 kV dapat terjaga secara optimal
A Culinary Recommendation System in Lombok Using Latent Dirichlet Allocation and Content-Based Filtering
Full text linkThis research develops a culinary recommendation system in Lombok by integrating the Latent Dirichlet Allocation (LDA) and Content-Based Filtering (CBF) methods. This integration aims to overcome the limitations of pure CBF, which relies solely on basic restaurant attributes and is less capable of capturing the semantic context of tourist reviews. Data was obtained through web scraping of Google Maps using the Apify.com platform, covering 825 restaurants and 20,114 reviews. The research stages included data collection, text preprocessing, topic modeling using LDA, feature engineering, similarity calculation using cosine similarity, and system evaluation. Evaluation was performed using Precision@K, Recall@K, F1-Score, and Mean Average Precision (MAP). The results show that the hybrid CBF+LDA model provides a significant improvement compared to pure CBF, with Precision@3 of 0.9333, Recall@3 of 0.1312, F1-Score of 0.2300, and MAP of 0.9628. These findings indicate that the integration of LDA topics enriches the semantic representation of reviews, thereby improving the relevance of recommendations. This research contributes to the development of artificial intelligence-based tourism recommendation systems and provides practical implications for promoting local cuisine, enhancing tourist experiences, and utilizing digital reviews as a basis for decision-making in the regional tourism sector.
Analisis Optimalisasi Perawatan Excavator Untuk Menunjang Produktivitas Unit
Full text linkMaintenance is an important daily activity that aims to ensure equipment or units can operate properly by reducing the risk of damage. One of the heavy equipment units used in mining projects is an excavator, but the high frequency of breakdowns in excavator units requires optimization of the maintenance that has been carried out. This study aims to analyze the performance and effectiveness of hydraulic excavator unit maintenance using the physical availability, mechanical availability, use of availability, mean time between failure, and mean time to repair calculation methods. The calculations show an 8.12% increase in the average PA, MA, and UA values and a 5.16-hour increase in MTBF. Meanwhile, the MTTR calculation results indicate a time reduction of 6.16 hours after optimization. The calculation results after optimization show that the maintenance carried out is effective and efficient to support the unit\u27s productivityPerawatan merupakan kegiatan penting yang dilaksanakan setiap hari yang bertujuan memastikan peralatan atau unit dapat beroperasi dengan baik dengan mengurangi risiko kerusakan. Salah satu unit alat berat yang digunakan pada proyek tambang adalah excavator, namun frekuensi breakdown yang tinggi pada unit excavator memerlukan optimalisasi perawatan yang telah dilakukan. Kajian ini bertujuan untuk menganalisis performa dan efektivitas perawatan unit hydraulic excavator dengan menggunakan metode perhitungan physical availability, mechanical availability, use of availability, mean time between failure, serta mean time to repair. Hasil dari perhitungan menunjukkan bahwa terdapat kenaikan rata-rata nilai PA, MA, dan UA setelah optimalisasi sebesar 8,12% serta kenaikan MTBF sebesar 5,16 jam. Untuk hasil perhitungan MTTR terjadi reduksi waktu sebesar 6,16 jam setelah dilakukan optimalisasi. Dari hasil perhitungan setelah optimaliasi menunjukkan bahwa perawatan yang dilakukan berjalan efektif dan efisien sehingga dapat menunjang produktivitas dari unit
Early Warning System Bencana Banjir Menggunakan LoRa Antar Node System
Full text linkIndonesia adalah salah satu negara yang beriklim tropis. Curah hujan yang tinggi menyebabkan banjir pada sungai yang tidak dapat diprediksi. Bencana banjir yang terjadi nampak tidak ada pencegahan secara efektif serta kurangnya sistem untuk memberikan peringatan sedini mungkin sebelum terjadinya bencana banjir agar kerugian dapat diminimalisir. Pemantauan bencana banjir harus dilakukan di tepi sungai dari hulu ke hilir. Pada lokasi tersebut sering tepi sungai berada di daerah hutan yang kondisi sinyal gsm lemah bahkan tidak ada. Kondisi tersebut menyebabkan sulitnya pengiriman data antar node ews ke penerima. Kesulitan tersebut dapat diatasi dengan menggunakan sebuah modul Lora. Lora mempunyai komunikasi menggunakan gelombang radio 455 Mhz. Gelombang tersebut dapat dipancarkan oleh modul dan dapat diterima oleh modul Lora di Reciver. Sehingga pengiriman data dapat dilakukan tanpa mengadalkan sinyal GSM. Lora juga dapat digunakan untuk pengiriman data menggunakan topologi jaringan seperti star, mesh, dll. Sistem peringatan dini bencana banjir menggunakan Lora didapatkan jarak maksimal komunikasi pada NLOS jarak maksmial komunikasi adalah 520 m dengan nilai RSSI terkecil -128 dan terbesar -147 dBm
Pemanfaatan Limbah Plastik PET Sebagai Filamen Printer 3D dengan Metode Pultrusi
Full text linkPolyethylene terephthalate (PET) plastic bottle waste can be recycled into 3D printer filament through pultrusion method. Some previous studies have identified the parameters of PET recycled filament, but have not yet deeply examined the effect of the combination of parameters including the level of roughness. This study aims to evaluate the effects of variations in bed and head temperatures and printing speed on the dimensions of 3D-printed PET filament, to analyze defects, and to assess surface roughness. The results showed that the best products were found at a head temperature of 265°C, a bed temperature of 80°C, and a speed of 35 mm/s. The dominant defects that appeared were under & over-extrusion, weak infill, and layer separation and splitting. Minimal defects were obtained at a head temperature of 265°C and 260°C with a bed temperature of 80°C at a speed of 35 mm/s. The lowest surface roughness results were in class N10, namely Ra = 16.137 µm. This study indicates that optimized parameters produce high quality, making PET a sustainable alternative material.
 
Studi Karakteristik Komposit Matrik Logam Al-Cu-Mg Dengan Penambahan SiC Disintesis Menggunakan Teknik Metalurgi Serbuk Diikuti Artificial Aging
Full text linkThe improvement of the characteristics of Al-Cu-Mg through SiC addition and precipitate formation can be achieved through powder metallurgy and artificial aging, which means that the correct amount of particles and holding time are important. This research aims to investigate the effect of SiC and time on microstructure change, mechanical properties, and electricity. The Al, Cu, Mg, and (1~2.0) wt.%SiC powder were mixed by horizontal milling and subsequent sintering at 500oC. The artificial aging at 180oC with (2, 4, 6) hour holding times. The hardness test, compression, electrical conductivity, and microstructural observation were carried out. The results show that the addition of SiC particles improves the strength and reduces the conductivity. The conductivity improvement obtained after aging. SiC particles tend to be dispersed between grain boundaries. Based on the data, it can be concluded that SiC and artificial aging have a positive effect on the mechanical properties of Al-Cu-Mg alloy
Prediksi Diabetes menggunakan Metode Ensemble Learning dengan Teknik Soft Voting
Full text linkDiabetes is a chronic disease characterized by high blood glucose levels due to the body\u27s inability to produce or use insulin effectively. This disease is one of the serious global health problems, and it has a significant impact; therefore, early detection is very important. Efforts to overcome this challenge can be made by applying machine learning, which provides a new and effective approach. This study aims to predict diabetes with a higher accuracy level through the Ensemble Learning Soft Voting method. In addition, the data balancing technique using SMOTE is applied to overcome the problem of imbalance in the data set. This study also compares various classification models using Machine Learning algorithms, namely LightGBM, XGBoost, and Random Forest. The test results show that the Random Forest model achieves the highest level of accuracy at 97.20%. In comparison, the Ensemble Learning Soft Voting method that combines the three algorithms has increased the accuracy to 97.74%. This Ensemble Learning approach has proven effective in significantly improving predictions and performing better than a single model
Perbandingan Pendekatan Machine Learning untuk Mendeteksi Serangan DDoS pada Jaringan Komputer
No full textDistributed Denial of Service (DDoS) attacks are a serious threat to computer network security. This study offers a comprehensive evaluation by considering accuracy, detection time, and model complexity in simulation scenarios. Using the CICDDoS2019 dataset, which includes modern attack variations and complete features, this research compares the effectiveness of Naïve Bayes (NB), Random Forest (RF), and Decision Tree (DT) algorithms in detecting DDoS attacks. The results show that RF achieves the highest accuracy (99.95%), while DT excels in recall (99.83%). These findings provide a foundation for developing hybrid ML-DL models to enhance real-time attack detection. However, limitations such as using a single dataset and offline simulations restrict the generalizability of results to real-world network conditions. This study highlights opportunities for more comprehensive future research in real-world scenarios.
 
Rancang Bangun Angklung Elektrik dengan Mode Otomatis dan Manual Menggunakan Teknologi Mikrokontroler dan Smartphone
Full text linkAngklung is a traditional Indonesian musical instrument originating from West Java. Angklung is composed of two to four bamboo tubes tied with rattan ropes and played by shaking them. The existence of angklung is currently starting to be replaced by modern musical instruments. This research aims to produce angklung integrated with microcontroller and smartphone technology. The use of microcontroller technology allows angklung to be automated without changing the character of the original art. This research method uses a quantitative approach from the design stage to the final test. The research showed that angklung successfully played songs automatically and manually. The tone suitability test results reach 100%. The sound intensity test recorded an average of 86.9 dB in automatic mode and 88.2 dB in manual mode. The power consumption test shows power usage of 1,378 Watts in automatic mode and 1,461 Watts in manual mode