Institut Teknologi Nasional: Jurnal Itenas Online
Not a member yet
1717 research outputs found
Sort by
ESTIMATION OF EMISSION TAX VALUE OF HOSPITALITY AND RESTAURANT INDUSTRY IN BOGOR CITY, WEST JAVA, INDONESIA
Get PDFThe number of hotels and restaurants in Bogor City has increased annually. According to the Bogor City Tourism and Culture Office (2018), the number of hotels rose from 53 units in 2016 to 87 units, while restaurants increased from 162 units to 680 units. This growth leads to higher CO2 emissions, while green open spaces remain static. This study aims to estimate CO2 emissions from the hotel and restaurant industry using the TIER-1 method, determine the urban park land needed to absorb these emissions using a quantitative descriptive approach, estimate the CO2 emission tax value based on the cost of creating urban parks, and propose alternative policy implications for emission tax implementation using a qualitative descriptive approach. The results indicate that hotels in Bogor City produce 3221 tons of CO2 per year, and restaurants produce 9583 tons per year. The current green open spaces are insufficient to absorb these emissions, necessitating additional urban park land. Specifically, the hotel industry requires 57 hectares of city park, and the restaurant industry requires 167 hectares. Funding for the development of these parks is to be sourced from emission taxes levied on hotels and restaurants. The proposed emission tax is Rp 3415 per room per night for hotels and Rp 239 per transaction for restaurants
Face Race Classification using ResNet-152 and DenseNet- 121
Get PDFABSTRAKPenelitian ini bertujuan untuk membandingkan hasil kinerja arsitektur ResNet-152 dan DenseNet-121 dalam mengklasifikasikan wajah berdasarkan ras. Ras yang diklasifikasikan terdiri dari 4 kelas: Putih, Hitam, India, dan Asia. Penelitian ini menggunakan parameter batch_size 32, optimizer, dan learning rate untuk meningkatkan kinerja model. Dua optimizer yang dibandingkan, yaitu Adam Optimizer dan Nadam Optimizer. Nilai learning rate yang dipertimbangkan adalah 0,0001 dan 0,001. Berdasarkan hasil percobaan klasifikasi wajah berdasarkan ras, baik arsitektur ResNet-152 maupun DenseNet-121 mencapai kinerja akurasi dan recall yang sama yaitu 0,788. Kinerja terbaik untuk presisi dan f1-score adalah ResNet-152. ResNet-152 memiliki presisi dan f1-score yang lebih baik masingmasing sebesar 0,376% dan 0,252%, jika dibandingkan dengan DenseNet-121. Oleh karena itu, ResNet-152 memiliki kinerja terbaik jika dibandingkan DenseNet-121 dalam klasifikasi wajah berbasis ras.Kata kunci: kinerja, ResNet-152, DenseNet-121, wajah, klasifikasi ABSTRACTThis study aims to compare the performance results of the ResNet-152 and DenseNet-121 architectures for classifying faces based on race. The classified race consists of 4 classes i.e.: White, Black, Indian, and Asian. The study used a batch size of 32, an optimizer, and a learning rate to improve model formation performance. Two optimizers are being compared, namely Adam Optimizer and Nadam Optimizer. The learning rate values considered are 0.0001 and 0.001. Based on the results of facial classification experiments based on race, both the ResNet-152 and DenseNet-121 architectures achieve the same accuracy and recall performance, namely 0.788. The best performance for precision and f1-score is ResNet-152. The ResNet-152 has better Precision and F1-Score of 0.376% and 0.252% respectively, in case it’s compared to DenseNet-121. Hence, it can be inferred that ResNet-152 surpasses DenseNet-121 in delivering superior performance outcomes for racial-based facial classification.Keywords: performance, ResNet-152, DenseNet-121, face, classificatio
Modification of Drivetrain and Control System Plastic Mulch Hole Puncher Vehicle
Get PDFA mechanical mulching becoming popular due to the shortage of labor [1]. Plastic Mulch Hole Puncher Vehicle have been developed from research about Design of a Remote Control System as a Semi-Automatic Plastic Mulch Hole Puncher [2] and Automatic Pest Spraying Vehicle Frame Design [3]. The drivetrain that has been developed uses 4 wheels so it can slip if it encounters muddy terrain. In this research, we modified the drivetrain like a tank so that the vehicle can move in all situations. In previous research, the control system used was Fly Sky Remote Control and Arduino MEGA to control the Plastic Mulch Hole Puncher. In this research, we modified the remote and controller using a pair of microcontroller and radio frequency modules. For the drivetrain, the method used in this research is a modification using a pair of chains with metal plates welded to each outer link and 4 sprocket for the left and right sides. The chains and sprockets used are for motorbikes, and the metal plates using ST37 with dimensions 60 x 15 x 3 mm. For the control system, the method used in this research is to combine data reception from the transmitter and actuator movement with Arduino UNO and nRF24L01 module. In vehicle, 11 Digital Pins of Arduino UNO connected to: nRF24L01 via adapter module, 2 BTS 7960 motor driver that connect to power windows motor for automotive use, and 2 relay module to drive 2 pneumatic DCV (Direct Control Valve) that connected with Mulch Hole Puncher. In transmitter, 7 Digital Pins of Arduino UNO connected to: nRF24L01 via adapter module and 2 push button for activated pneumatic DCV /Mulch Hole Puncher, meanwhile 2 Analog Pins connected to joystick for control vehicle movement (froward/backward, turn left/right). The results of this research, the vehicle can be driven using a new drivetrain and controlled by Arduino UNO and nRF24L01 using radio frequency.Keywords: tank drivetrain, open-source microcontroller, radio frequenc
Data Storage Database PostgreSQL and JSON File Format in Golang Using Gin-Gonic and Gin-Gonic with GORM
Get PDFProficient data management and storage are imperative. Among the various programming languages and frameworks available, Golang Gin-Gonic and Golang Gin-Gonic with GORM are widely favored by developers for their speed and concurrent processing efficiency. Golang Gin-Gonic is especially valued for creating high-performance applications, while GORM extends Golang’s capabilities with a powerful GORM for database operations. Prior studies have emphasized Golang's effectiveness in data exchange and its superior response speed and resource efficiency compared to Java and Python. This study aims to analyze the performance of Golang Gin-Gonic and Golang Gin-Gonic with GORM concerning data storage, focusing on PostgreSQL databases and JSON file formats. PostgreSQL was selected for its robustness as an open-source RDBMS, while JSON was chosen for its lightweight and readable format. The research assesses the execution speed and concurrency performance of both frameworks during data storage tasks involving PostgreSQL and JSON. The study investigates the performance of Gin-Gonic and Gin-Gonic with GORM in handling concurrent data storage operations in PostgreSQL and JSON formats. Performance tests measured the duration and anomalies in data storage across three dummy data sizes, 1000, 2000, and 3000. The results indicated that, for basic Golang Gin-Gonic, JSON processing was generally faster than PostgreSQL, with a growing performance gap as data size increased. Specifically, JSON processing was 53.63% quicker for 1000 dummy data, 24.14% quicker for 2000 dummy data, and 43.76% quicker for 3000 dummy data. Conversely, Golang Gin-Gonic with GORM showed superior performance with PostgreSQL, being 21% faster for 1000 dummy data, 20.54% faster for 2000 dummy data, and 33.2% faster for 3000 dummy data compared to JSON processing. These findings imply that while JSON is more suitable for simpler configurations with basic Golang Gin-Gonic, PostgreSQL integrated with GORM offers enhanced performance for handling larger and more intricate data sets. This research provides valuable guidance for software developers in choosing the appropriate framework based on their specific requirements, considering factors such as speed, concurrency, and data storage type.Keywords, Golang, Gin-Gonic, GORM, Data Storage, Performance analysi
Perancangan dan Simulasi Kompressor Sentrifugal dengan fluida SCO-2 Pada Siklus Brayton Regeneratif
Get PDF Di Indonesia, terdapat potensi energi baru dan terbarukan (EBT) yang cukup besar dan beragam. Salah satu sumber energi terbarukan yang tersedia adalah biomassa. Pemanfaatan Siklus Brayton dengan karbon dioksida sebagai fluida kerja pada fase superkritis merupakan salah satu metode pemanfaatan biomassa. Karena karbon dioksida tersedia secara luas di Bumi dan memiliki kepadatan tinggi pada fase superkritis, mesin turbo kompak dapat digunakan. Hal ini memungkinkan desain turbin, kompresor, dan alternator yang kecil. Keuntungan Siklus Brayton adalah penggunaan regenerator untuk pemulihan panas di sisi keluar turbin. Tujuan dari proyek ini adalah untuk membangun kompresor sentrifugal untuk Siklus Regeneratif Brayton. Output bersih kompresor yang diharapkan adalah 40 kW pada 70.000 rpm. Fluida kerja karbon dioksida superkritis (S-CO2) yang digunakan dalam siklus regeneratif Brayton ditujukan untuk temperatur masuk turbin 800 K, temperatur masuk kompresor 320 K. Menurut desain siklus, turbin dan kompresor memiliki daya masing-masing sebesar 113,84 kW dan 60,53 kW. Pendekatan desain geometris yang digunakan sejalan dengan beberapa literatur terkait penelitian. Hasil desain kompresor kemudian disimulasikan oleh computational fluid dynamic (CFD). Berdasarkan temuan pemodelan CFD, kompresor sentrifugal membutuhkan daya sebesar 69,89 kW dengan efisiensi isentropik sebesar 60,03 persen pada kondisi desain. Daya bersih yang dihasilkan sebesar 43,39 kW berdasarkan hasil simulasi CFD. Kata kunci: siklus Brayton, karbon dioksida superkritik, kompreso, perancangan dan simulasi Abstract In Indonesia, there is a substantial and varied potential for new and renewable energy. One of the renewable energy sources that is present practically everywhere is biomass. Utilizing the Brayton Cycle with carbon dioxide as the working fluid in the supercritical phase is one method of utilising biomass. Because carbon dioxide is widely available on Earth and has a high density in the supercritical phase, compact turbomachinery can be used. This allows for the small design of the turbine, compressor, and alternator. The Brayton Cycle's advantage is the employment of a regenerator for heat recovery on the turbine's exit side. The purpose of this project is to build a centrifugal compressor for the Regenerative Brayton Cycle. The intended net output of the compressor is 40 kW at 70,000 rpm. The supercritical carbon dioxide working fluid (S-CO2) used in the regenerative Brayton cycle is intended for turbine inlet temperatures of 800 K, compressor inlet temperatures of 320 K. According to the cycle's design, the turbine and compressor have respective powers of 113.84 kW and 60.53 kW. An approach to geometric design is used that is in line with some of the research-related literature. The outcomes of the compressor design are then subjected to CFD simulations. According to the CFD modeling findings, the centrifugal compressor requires 69.89 kW of power with an isentropic efficiency of 60.03 percent under design conditions. The net power produced is 43.39 kW based on the outcomes of the CFD simulation. keywords ; Brayton cycle, supercritical karbon dioxide, compressor, design and simulatio
Analisis Perilaku Struktur Gedung Ber-Layout L Delapan Lantai dengan Penambahan Sistem Dilatasi
Get PDFABSTRAKBerdasarkan Peraturan Menteri PU no 29/PRT/M/2006 menyatakan bahwa bangunan gedung dengan bentuk T, L atau U harus dilakukan pemisahan struktur atau dilatasi untuk menghindari terjadinya benturan elemen akibat gempa atau penurunan tanah. Terlebih pada daerah dengan risiko terhadap gempa yang cukup tinggi. Maka dari itu bentuk denah bangunan pada daerah rawan gempa disarankan memiliki bentuk yang beraturan atau simetris dan sederhana agar memiliki perilaku struktur yang baik. Pada penelitian ini, dilakukan analisis perilaku struktur pada bangunan layout L dengan penambahan dilatasi. Analisis yang digunakan adalah analysis respon spectrum dan static ekuivalen mengacu pada SNI 1726:2019. Hasil dari penilitian ini menunjukkan bahwa penambahan dilatasi pada bangunan gedung dapat mengurangi kekakuan bangunan dan hal ini berpengaruh pada perilaku struktur bangunan yang terjadi. Kemudian, penggunaan dilatasi mampu mencegah terjadinya konsetrasi tegangan pada pelat yang cukup besar pada bangunan dengan layout L.Kata kunci: gempa, perilaku struktur, dilatasi, SNI 1726:2019 ABSTRACTBased on “Peraturan Menteri PU No. 29/PRT/M/2006” states that buildings with a T, L or U shape must be separated from the structure or dilated to avoid collisions with elements due to earthquakes or land subsidence. First, in areas with a high risk of earthquakes. Therefore, it is suggested that the shape of a building plan in an earthquake-prone area should have a regular or symmetrical and simple shape so that it has good structural behavior. In this study, an analysis of the structural behavior of the L layout building was carried out with the addition of dilation. The analysis used is response spectrum analysis and static equivalent which refers to SNI 1726:2019. The results of this study indicate that the addition of dilation to buildings can reduce the rigidity of buildings and this affects the behavior of building structures that occur. Then, the use of dilation is able to prevent the stress concentration on the slab which is quite large in buildings with L layout.Keywords: earthquake, structural behavior, dilation, SNI 1726:2019
Prediksi Kanker Paru menggunakan Grid search untuk Optimasi Hyperparameter pada Algoritma MLP dan Logistic Regression
Get PDFABSTRAKKanker paru merupakan penyebab utama kematian akibat kanker di seluruh dunia. Prediksi dini kanker paru-paru telah banyak dilakukan, baik berbasis citra maupun data mentah. Prediksi kanker paru berbasis citra memberikan dampak positif dalam diagnosis dini, namun pendekatan berbasis data mentah juga penting dalam memahami faktor risiko dan kondisi yang dapat mempengaruhi perkembangan kanker. Penelitian ini mengusulkan sistem prediksi dini kanker paru dengan basis data klinis dan demografi, menggunakan Multi-Layer Perceptron (MLP) dan logistic regression dengan pemanfaatan grid search optimizer. Kedua model mencapai tingkat akurasi, presisi, recall, dan f1-score sebesar 1, optimal dalam melakukan prediksi data. Pada logistic regression, solver liblinear, penalty L1, dan nilai C yang lebih tinggi berkontribusi pada peningkatan akurasi. Sedangkan pada MLP, konfigurasi aktivasi tanh dan solver adam menghasilkan akurasi yang lebih baik. Hasil ini memberikan keyakinan implementasi MLP dan logistic regression, memiliki potensi dalam mendukung prediksi kanker paru-paru.Kata kunci: kanker paru, multi-layer perceptron, logistic regression, grid search ABSTRACTLung cancer is a leading cause of cancer-related deaths worldwide. Early prediction of lung cancer has been widely conducted, both based on images and raw data. Image-based lung cancer prediction has a positive impact on early diagnosis, but a raw data-driven approach is also crucial for understanding risk factors and conditions that can influence cancer development. This research proposes an early lung cancer prediction system using clinical and demographic data, employing Multi-Layer Perceptron (MLP) and logistic regression with the utilization of grid search. Both models achieved an accuracy, precision, recall, and f1-score of 1, optimal in classifying data. In logistic regression, the liblinear solver, L1 penalty, and higher C values contributed to increased accuracy. Meanwhile, in MLP, the configuration of tanh activation and adam solver yielded better accuracy. Theseresults instill confidence that the implementation of MLP and logistic regression has significant potential in supporting lung cancer prediction.Keywords: lung cancer, multi-layer perceptron, logistic regression, grid searc
Analisis Perancangan dan Pemasangan PLTS Kapasitas 1,1 MWp pada Pabrik Farmasi di Kota Semarang
Get PDFABSTRAKBiaya utilitas adalah salah satu komponen terbesar dalam biaya produksi sebuah pabrik farmasi. Dari total biaya utilitas, 63% berasal dari pemakaian energi listrik. Jika energi listrik tersebut dapat diperoleh dari Energi Baru Terbarukan (EBT) hingga 10.65%, maka akan berdampak positif bagi biaya produksi. EBT yang dapat dipakai adalah Pembangkit Listrik Tenaga Surya (PLTS) dengan memanfaatkan atap gedung produksi. Selain penghematan perlu diperhatikan dampak interkoneksi PLTS terhadap arah aliran daya, kestabilan sistem kelistrikan saat gangguan, dan potensi terhadap sambaran petir ke instalasi PLTS. Optimalisasi desain PLTS dengan Helioscope menunjukkan kapasitas PLTS yang dapat dipasang hingga 1,1 MWp. Hasil analisis aliran daya dengan ETAP menunjukkan bahwa daya reaktif yang mengalir balik ke jaringan PLN sangat kecil. Sistem kelistrikan dengan injeksi daya dari PLTS ini dapat stabil setelah mengalami gangguan. Berdasarkan metode sudut perlindungan maka untuk 9 bangunan yang dipasang PLTS tersebut diperlukan proteksi petir level IV.Kata kunci: energi surya, kestabilan sistem tenaga, aliran daya, perlindungan sambaran petir ABSTRACTUtility costs are one of the largest components in the production expenses of a pharmaceutical plant. Among utility costs, 63% of total cost takes from electricity consumption. If this electricity can be supplied from Renewable Energy (RE) up to 10.65%, it will have a positive impact on production costs. The viable RE source is PhotoVoltaic Solar Power (PV) by utilizing the building's production area rooftop. The others impact must be given to the PV system's effects on power flow direction, electrical system stability during disturbances, and susceptibility to lightning strikes on the PV installation. Optimation result of the PV system design using Helioscope indicates a capacity of up to 1,1 MWp. Power flow analysis using ETAP results demonstrate minimal reactive power flowing back to the grid. The electrical system with power injection from the PV system regains stability after disturbance. Based on the angle protection method, a lightning protection level IV is required for the 9 buildings with PV systems.Keywords: Solar energy, power system stability, power flow, lightning strike protection
Rekomendasi Jumlah Pupuk Urea untuk Tanaman Padi berdasarkan NDVI Clustering pada Citra Multispektral
Get PDFABSTRAKPupuk merupakan hal yang penting bagi tanaman. Nilai NDVI dari citra multispektral lahan pertanian dapat digunakan untuk menentukan kebutuhan pupuk pada tanaman. Pada makalah ini, telah direalisasikan layanan rekomendasi pemupukan tanaman padi berdasarkan NDVI clustering. Citra sawah diambil menggunakan kamera Multispectral Mapir Survey 3W RGN yang dipasang pada DJI Mavic 2 Pro. Penentuan kebutuhan pupuk tanaman padi dilakukan dengan menggunakan metode K-Means clustering pada nilai NDVI. Hasil yang didapat dari proses clustering dimasukan ke dalam rumus rekomendasi pemupukan yang mengacu kepada BWD. Dari hasil pengujian menunjukan platform dapat memberikan rekomendasi pemupukan untuk tanaman padi. Selisih antara hasil rekomendasi jumlah pupuk menggunakan platform dan BWD yaitu 1.29% pada pukul 10.00 pagi, 3.35% pada pukul 12.00 siang, dan 2.40% pada pukul 04.00 sore. Selisih hasil perhitungan tersebut disebabkan karena adanya perbedaan intensitas cahaya matahari.Kata kunci: multispektral, K-Means Clustering, NDVI, platform, padi, pupuk ABSTRACTFertilizer is a crucial component for plants. NDVI values from multispectral imagery of agricultural land can be used to determine fertilizer requirements. In this paper, a rice plant fertilization recommendation service based on NDVI clustering has been realized. Rice field images were taken using the Multispectral Mapir Survey 3W RGN camera mounted on the DJI Mavic 2 Pro. Determination of fertilizer needs for rice plants is carried out using the K-Means clustering method on the NDVI value. The results obtained from the clustering process are entered into the fertilization recommendation formula which refers to BWD. The test results showed that the platform can provide fertilizer recommendations for rice plants. The difference between the recommended amount of fertilizer using the platform and BWD is 1.29% at 10 a.m, 3.35% at 12 noon, and 2.40% at 4 p.m. The difference in the results of these calculations is due to differences in the intensity of sunlight.Keywords: multispectral, K-Means Clustering, NDVI, platform, rice, fertilize
4.5 kW High Frequency Transformer Design for Dual Active Bridge (DAB)
Get PDFABSTRAKIndonesia bertujuan untuk beralih dari bahan bakar fosil ke sumber energi terbarukan, dengan target integrasi sebesar 23% pada tahun 2025 dan 31% pada tahun 2050. Transisi ini menghadapi tantangan akibat sifat terputus-putus dari sumber energi terbarukan yang memengaruhi kualitas listrik. Solid State Transformer (SST) muncul sebagai solusi. Dalam penelitian ini, sebuah trafo frekuensi tinggi dirancang untuk konverter Dual Active Bridge (DAB), dengan leakage inductance menjadi parameter penting. Berdasarkan perhitungan yang dilakukan, menunjukkan kebutuhan leakage inductance adalah sebesar 277 uH untuk DAB. Untuk memenuhi kebutuhan daya dan nilai leakage inductance tersebut, trafo dengan inti EE48020, 87 lilitan non-seksional, dan ketebalan isolasi 8,4 mm dapat dikembangkan. Hasil simulasi mengkonfirmasi nilai leakage inductance yang dihasilkan sebesar 268,95 uH.Kata kunci: tranformator frekuensi tinggi, dual active bridge, solid state transformer, kebocoran induktansi, geometri inti ABSTRACTIndonesia aims to shift from fossil fuels to renewable energy sources, targeting 23% integration by 2025 and 31% by 2050. This transition faces challenges due to the intermittent nature of renewable sources, impacting power quality. Solidstate transformers (SST) emerge as a solution. In this study, a high-frequency transformer (HFT) is designed for the dual active bridge (DAB), with leakage inductance being a crucial parameter. Calculations indicate a 277 uH requirement for the DAB. To meet power needs and leakage inductance values, an HFT with an EE48020 core, 87 non-sectional turns, and 8.4 mm insulation thickness is developed. Simulation results confirm a leakage inductance of 268.95 uH for the HFT.Keywords: high frequency transformer, dual active bridge, solid state transformer, leakage inductance, core geometr