E-Journal Politeknik Negeri Cilacap
Not a member yet
919 research outputs found
Sort by
Interpretable Deep Learning Model for Grape Leaf Disease Classification Based on EfficientNet with Grad-CAM Visualization
Get PDFGrape leaf diseases pose a significant threat to agricultural productivity, especially in regions with fluctuating climatic conditions that create favorable environments for pathogen growth. Early and accurate disease detection is essential for preventing severe crop losses. Traditional manual inspection methods are inefficient and prone to human error, highlighting the need for an automated approach. This study proposes a computer vision-based solution using Convolutional Neural Networks (CNN) improved by EfficientNetB0 to classify grape leaf diseases. The model was trained on a publicly available dataset from Kaggle, which consists of 9,027 images in four classes: ESCA, Leaf Blight, Black Rot, and Healthy. Each image has a resolution of 300 × 300 pixels with a 24-bit color depth, ensuring sufficient detail for analysis. To enhance model performance, data augmentation and hyperparameter tuning were applied. The EfficientNetB0 model was employed due to its strong feature extraction capabilities and computational efficiency. The proposed model achieved 99.36% accuracy, with evaluation metrics including precision (99%), recall (99%), and F1-score (99%), demonstrating its reliability in distinguishing disease categories. Further analysis using a confusion matrix and Grad-CAM visualization provided insights into the model’s decision-making process. The results indicate that this deep learning-based approach is highly effective for grape leaf disease classification. Future research can explore real-time field data collection, attention mechanisms, and self-supervised learning to further improve classification accuracy and model generalization for large-scale agricultural applications
TARKAM: The Advanced Robotic Kicker and Automation Machine for Goalkeeper Training
Get PDFThis research aims to design and implement a ball-throwing robot that is used to train goalkeeper skills, such as reflexes and the ability to read the direction of the ball. The main focus of the research is to develop a ball throwing system that can provide a variety of shots with high precision, as well as overcome the limitations of manual training that relies on the individual skills of the kicker. This ball-throwing robot is controlled through a smartphone using a Bluetooth HC-05 module as a means of communication, and is equipped with two DC spindle motors, two DC PG36 motors, and two DC 12V motors to regulate the direction and speed of the ball. The ball direction and rotation control uses PID (Proportional-Integral-Derivative) control to ensure stable and accurate ball launching. The system dynamically adjusts the ball speed and direction based on position and angle sensor feedback. Tests were conducted at three different distances, namely 5 meters (100% accuracy), 7 meters (100% accuracy), and 11 meters (80% accuracy). The test results show that this ball-throwing robot is able to deliver shots with high precision, move flexibly and quickly, and adjust the direction and speed of the ball effectively. The results of the ANOVA test (p < 0.005) showed a statistically significant difference in average firing accuracy at all three distances. This research makes a practical contribution to improving the effectiveness of goalkeeper training, as well as offering a more efficient solution in football training. This research makes a practical contribution in improving the effectiveness of goalkeeper training, as well as offering a more efficient solution in soccer training
Analisa Kinerja Setting Rele Overall Differensial pada Pembangkit Listrik Tenaga Panas Bumi PT. Pertamina Geothermal Energi Area Karaha
Get PDFPenelitian ini bertujuan untuk menganalisis kinerja setting Rele Overall Diferensial pada sistem proteksi generator dan transformator di Pembangkit Listrik Tenaga Panas Bumi PT. Pertamina Geothermal Energi Area Karaha. Latar belakang penelitian ini dilatarbelakangi oleh pentingnya sistem proteksi dalam mencegah kerusakan peralatan akibat gangguan hubung singkat, terutama pada lingkungan pembangkit listrik dengan karakteristik operasional yang kompleks. Metode penelitian dilakukan dengan mengumpulkan data spesifikasi peralatan dari lapangan, melakukan perhitungan matematis untuk menentukan arus rating, rasio CT, error mismatch, arus diferensial, dan arus restrain, serta melakukan simulasi gangguan hubung singkat (baik di dalam maupun di luar zona proteksi) menggunakan perangkat lunak ETAP. Hasil penelitian menunjukkan bahwa Rele Overall Diferensial bekerja optimal dengan memberikan perintah trip saat terjadi gangguan internal, sedangkan pada gangguan eksternal nilai arus diferensial berada dalam batas aman sehingga tidak memicu operasi rele. Analisis kurva karakteristik kerja rele mengungkapkan bahwa setting rele yang tepat, melalui penentuan slope dan arus setting, dapat meningkatkan selektivitas dan keandalan sistem proteksi. Kontribusi penelitian ini adalah menyediakan acuan perhitungan dan simulasi yang dapat digunakan untuk mengoptimalkan setting proteksi pada sistem tenaga listrik, khususnya dalam konteks pembangkit tenaga panas bumi, sehingga meningkatkan keandalan dan keselamatan operasional
Efficacy of Liquid Waste Reduction using Anaerobic and Aerobic Median Biofilters in Tofu Factory X, Pematang Sulur, Jambi City
Get PDF Tofu is a popular soy-based food. Tofu manufacturing produces wastewater that can pollute the environment, and waste discharged into rivers must meet wastewater quality standards. Wastewater treatment can increase factory operating costs. The purpose of this study was to determine the effectiveness of reducing Tofu Factory X\u27s wastewater parameters, namely BOD, COD, TSS, and pH. Research Methods 1) observation and data collection on water discharge for daily manufacturing operations, 2) calculation of equalization basin plan, anaerobic and aerobic biofilters, oxygen requirements and blowers, 3) raw water and wastewater quality testing from the design of the wastewater treatment plant of Tofu Factory X, and 4) calculation of the reduction efficiency of BOD, COD, TSS and pH and comparison with the Minister of Environment Regulation No. 5 of 2014. The research results obtained showed the reduction efficiency of BOD pollution by 30.75%, COD by 35%, TSS by 68.08% and pH by 4.55. The wastewater treatment in this study did not fully demonstrate the expected efficiency, as adjustments had to be made to the required air quantity, temperature, and residence time.
Keywords: anaerobic and aerobic, biofilter, liquid waste, tofu factory, wastewater quality.
Analisis Pengujian Statis pada Rangka Kendaraan Listrik Niaga Roda Tiga dengan Metode Elemen Hingga
Get PDFThe frame is an important component in the automotive industry. With the development of computer systems, structural frame testing can be carried out by simulation. ANSYS Workbench is a popular program for static testing of frames. This research analyzes the parameters of equivalent stress, total deformation, and safety factors in the ladder frame of three-wheeled electric vehicles. Analyzing these three parameters is expected to provide an overview of the maximum load the frame can receive. The materials used are aluminum alloy and carbon steel, and the vertical load is 215 Kg (2,107 Newton) and 265 Kg (2,597 Newton). The results show that both materials can accept variations in the vertical load given, as seen from these three parameters. In more detail, carbon steel has better quality than aluminum alloy. Carbon steel produces the highest maximum equivalent stress value of 29,175 MPa and 35.96 MPa, and the lowest maximum total deformation values are 0.098137 mm and 0,12096. The minimum safety factor values for carbon steel are 10,06 and 8,1619
Analisis Sentimen Media Sosial X Terhadap Kenaikkan PPN di Indonesia Menggunakan Algoritme Naïve Bayes dan Support Vector Machine (SVM)
No full textOne of the ways to increase state revenue is by raising the Value-Added Tax (VAT). However, implementing a VAT hike policy often elicits both positive and negative responses from the public. With the presence of social media, people can voice their opinions about government policies, including through social media platform X. This study aims to analyze public sentiment on social media X using the Naïve Bayes and Support Vector Machine (SVM) algorithms. The research compares the highest accuracy results before and after the balancing process. The dataset comprises 2,852 rows in CSV format. The findings indicate that the SVM algorithm achieves an accuracy of 98% before balancing and 97% after balancing, while Naïve Bayes achieves an accuracy of 97% before balancing and 90% after balancing. Overall, both algorithms demonstrate good and balanced performance.
 
Simulasi Computational Fluid Dynamics (CFD) untuk Optimalisasi Proses Perekatan pada Oven Bambu Laminasi
Get PDFThe utilization of bamboo in architecture and construction as an eco-friendly alternative to wood is steadily increasing. While ovens are crucial tools in the production of laminated bamboo, particularly for heating during the bonding process, research on ovens specifically designed for bamboo lamination remains scarce. This study aims to optimize the design of laminated bamboo ovens using Computational Fluid Dynamics (CFD) simulations to achieve uniform heat distribution and maximize thermal efficiency. Three design iterations were tested: Iteration 1 with an air velocity of 4 m/s, Iteration 2 with 1.5 m/s, and Iteration 3 with 3 m/s. The results revealed that Iteration 1 exhibited uneven heat distribution, with initial temperatures reaching 1175 K before dropping sharply to 800 K. Iteration 2 showed slower initial heating, achieving a final temperature of 360 K, but heat distribution remained suboptimal. Iteration 3 delivered the best performance, achieving uniform and stable heat distribution near the target temperature of 473 K (200 °C). Overall, Iteration 3 demonstrated the most efficient thermal performance, not only meeting the target temperature with consistent heat distribution but also enhancing the overall heating efficiency of the oven.Bambu, sebagai bahan bangunan yang berkelanjutan, memiliki banyak keunggulan, namun aplikasinya terkendala oleh bentuk alami yang melingkar. Oleh karena itu, produk-produk bambu olahan seperti laminated bamboo lumber (LBL) dan cross-laminated bamboo (CLB) dikembangkan untuk meningkatkan fungsionalitasnya. Perlakuan termal pada bambu dapat meningkatkan ketahanannya terhadap cuaca dan organisme perusak. Penelitian ini menggunakan simulasi dinamika fluida komputasional (CFD) dengan ANSYS Fluent untuk menganalisis distribusi suhu dan aliran udara dalam oven yang digunakan untuk pemanasan bambu laminasi. Hasil simulasi menunjukkan bahwa model iterasi 3, dengan pengaturan kecepatan aliran udara 3.5 m/s, menghasilkan distribusi suhu yang lebih merata dan mendekati target 473 K di hampir seluruh area oven, sehingga meningkatkan efisiensi termal dan konsistensi pemanasan. Hasil ini menunjukkan potensi model iterasi 3 untuk memperbaiki kualitas produk bambu laminasi dan efisiensi operasional oven. Penelitian ini menambah pengetahuan terkait aplikasi CFD dalam industri pengolahan bambu
Studi Potensi Emisi Gas Rumah Kaca Menggunakan Metode IPCC Serta Arahan Pemanfaatan Sampah Organik Yang Dihasilkan Berdasarkan Aspek Teknis Di Kecamatan Balikpapan Barat
Get PDFTerdapat empat sektor utama yang diketahui berkontribusi dalam peningkatan emisi gas rumah kaca salah satunya yaitu sektor limbah padat. Aktivitas antropogenik memiliki potensi untuk melepaskan emisi GRK dan hal tersebut terdapat di Kecamatan Balikpapan Barat. Keberagaman aktivitas masyarakat Kecamatan Balikpapan Barat juga memicu peningkatan timbulan sampah. Penelitian ini bertujuan guna mengidentifikasi timbulan, komposisi, karakteristik sampah organik, menginventarisasi emisi GRK, serta merekomendasikan arahan pengolahan sampah organik berdasarkan aspek teknis. Mengacu pada SNI 19-3964-1994, hasil pengukuran lapangan menyatakan bahwa besaran timbulan sampah pemukiman sebesar 0,145 Kg/orang/Hari dan 0,1 Kg/m2/Hari besaran timbulan yang dimiliki Pasar Pandansari. Sampah organik mendominasi hasil pengukuran komposisi sebanyak 80% dan berpotensi untuk dikomposkan. Karakteristik sampah Kecamatan Balikpapan Barat memiliki kadar air (90,1%), C-organik (43,89%), N-organik (2,19%), dan nilai rasio C/N adalah 20. Menurut data sampling yang didapat, dari sektor limbah padat Kecamatan Balikpapan Barat tahun 2022 berkontribusi melepaskan sejumlah emisi GRK hanya pada penimbunana sampah sebesar 2.073,57 CO2-eq Ton/Tahun. Perhitungan estimasi GRK dianalisis dengan dua skenario dimana skenario 1 diasumsikan 100% sampah yang dihasilkan diangkut ke TPA tanpa adanya upaya reduksi dan skenario 2 diasumsikan 70% diangkut ke TPA dan 30% dilakukan reduksi dari sumber. Skenario 2 merupakan alur terbaik untuk diadakan pengolahan sampah dimana selisih emisi GRK sebesar 622,07 CO2-eq Ton/Tahun saat hanya ditimbun di TPA dengan total emisi pada penimbunan sampah sebesar 1.451 CO2-eq Ton/Tahun dan pada pengomposan sebesar 179,52 CO2-eq Ton/Tahun. Sampah organik di Kecamatan Balikpapan Barat dapat dimanfaatkan sesuai dengan hasil analisis dan inventarisasi emisi GRK diantaranya sebagai kompos, biodigester, pengkonversian sampah menjadi energi listrik, dan penerapan 3R (reduce – reuse – recycle).
Kata kunci : Gas rumah kaca, Karakteristik sampah, Komposisi sampah, Pemanfaatan sampah organik, Timbulan sampa
Parallel Computing Applied to A Three-Modality Biometric Recognition System using Task Parallel Library
Get PDFThis study focuses on optimizing the performance of a three-modality biometric recognition system (fingerprints, facial and voice recognition) with global decision fusion, designed for access control to secure areas. When the biometric database contains a large volume of information, the verification module\u27s processing time increases considerably due to the complexity of template comparisons. To address this issue, we implemented an optimization strategy based on parallel programming, specifically targeting the intensive processing loops within the verification module. Using Microsoft\u27s Task Parallel Library, we parallelized all critical loops associated with the three biometric modalities. By effectively exploiting for and foreach statements, our parallelized implementation enables optimal distribution of tasks across available processor cores. We validated our approach by conducting repeated experiments on data sets of varying sizes (50 to 600 individuals), with a rigorous analysis of temporal performance. The results show a significant reduction in execution times: for 600 entries, the processing time goes from 1.68 ms in sequential mode to 0.77 ms in parallel mode. These performances were evaluated over several iterations to ensure the statistical reliability of the results, in particular by calculating averages and standard deviations and including error bars in the comparative graphs. The practical implications of this work are significant: the module can be deployed in corporate security systems, airports or banks, while respecting ethical considerations and privacy constraints. Finally, this work paves the way for future extensions, including the integration of other biometric modalities, deployment on distributed clusters or the adoption of more advanced parallelization frameworks
PENERAPAN METODE QUALITY FUNCTION DEPLOYMENT (QFD) DALAM PERANCANGAN DAN PEMBUATAN ALAT PEMANENAN KELAPA SAWIT BERMOTOR PADA DI INDUSTRI KELAPA SAWIT : PERANCANGAN DAN PEMBUATAN ALAT PEMANENAN KELAPA SAWIT BERMOTOR
No full textIn the oil palm plantation industry, several motorized palm oil harvesting equipment already exist in the palm oil industry market. Several motorized palm harvesting equipment, such as STIHL PC 70 and Tanika TS-5, are on the market. These two machines are rarely used because the tool\u27s price is still high compared to the manual method. One part that makes both tools expensive is the gearbox. In addition, this part is the most often damaged so it requires a long repair time and increases the time to harvest oil palm. This research aims to design a gearbox for oil palm harvesting equipment that is low-cost, lightweight, and tough. The Quality Function Deployment (QFD) method was chosen to prototype the palm oil harvesting gearbox. The results of this research obtained a prototype gearbox that is lightweight and has a tough mechanical system. In addition to its manufacture, which is carried out independently and using local materials, the production cost of the gearbox is low, even when it is still in prototype form