Claim Missing Document
Check
Articles

Microbubble Measurements using Image Processing with the YOLOv8 Comparison Model Julian, James; Ulhaq, Faiz Daffa; Dewantara, Annastya Bagas; Purba, Riki Hendra; Wahyuni, Fitri; Junaedi, Thomas
Journal of Applied Sciences and Advanced Technology Vol. 6 No. 3 (2024): Journal of Applied Sciences and Advanced Technology
Publisher : Faculty of Engineering Universitas Muhammadiyah Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24853/jasat.6.3.109-116

Abstract

Gas-liquid two-phase is a situation where the gas phase of a liquid coexists together. The presence of gas that forms a region in the liquid environment causes the formation of bubble flow. The parameters of the bubble flow carry important information about the behavior and characteristics of the bubble. This research was carried out by detecting the size and area of the bubble using YOLOv8-based image processing by comparing the model's performance to produce improvements in inference time, increase accuracy, and reduce computational load. Bubble images were collected by adding 0.4 mm copper wire as a comparison to convert mm to pixels; then, the images were labeled and trained with various YOLOv8 models. Confusion matrix, precision and recall are used as comparative evaluation materials for the YOLOv8 model to obtain good model performance. In this study, the AUC of the Precision and Recall curve closest to the value 1 is the YOLOv8m model of 0.990. The comparison results of the matrix evaluation with the best model are the YOLOv8m model with mAP of 99.00% and F1-score of 96.86%. Microbubble measurements are calculated from the output of the YOLOv8 model by converting pixel units to mm. The model used in bubble measurements is the model with the best evaluation results and the model that gets the smallest radius value by considering measurement uncertainty, namely YOLOv8m with a minimum radius of 0.66 ± 0.04 mm..
Enhancing the accuracy of low-cost thermocouple devices through deep-wavelet neural network calibration Julian, James; Wahyuni, Fitri; Dewantara, Annastya Bagas; Winarta, Adi; Putra, Nandy
International Journal of Electrical and Computer Engineering (IJECE) Vol 14, No 3: June 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v14i3.pp2625-2633

Abstract

Data collection using thermocouple sensors in low-cost data acquisition is prone to noise interference, which could reduce the data quality. Noise sources such as cold junction compensators, electromagnetic interference, and Johnson noise can significantly affect the reliability and accuracy of conventional measurements. This study aims to improve the quality of thermocouple sensor readings on low-cost data acquisition using calibration method based on deep learning and the denoising process using a wavelet transform. This taken approach successfully increase the accuracy value of 97.67% with a mean absolute error (MAE) of 0.2. The precision also increases of 262.7% as indicated by the result of signal-to-noise ratio (SNR) with a value of 105.29 dB. Comparative analysis was carried out against National Instruments® device and it was found that deep-wavelet method had a lower and higher of MAE and SNRdB values of 16.67% and 0.8% respectively. This study shows that the denoising-calibration method with deep-wavelet can improve the accuracy and reliability of data from low-cost thermocouple devices.
Design of smoke detection system using deep learning and sensor fusion with recursive feature elimination cross-validation Julian, James; Bagas Dewantara, Annastya; Wahyuni, Fitri
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 13, No 2: June 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v13.i2.pp1658-1667

Abstract

The fire safety system is an important component that controls material and immaterial losses. Fire disasters are generally indicated by the appearance of excess smoke and changes in temperature, pressure, and changes in other parameters in the environment. Conventional smoke sensors are limited in reading parameter changes around their environment, making them less effective in early fire detection. This study aims to design a smoke detection system as an early fire detection system, using sensor fusion based on deep learning using the recursive feature elimination method with cross-validation (RFECV) using a random forest classifier used to select optimal parameters from public datasets as the basis for determining the sensor to be used. Based on the RFECV optimal feature, a deep learning algorithm was performed and obtained an accuracy of 0.99, a precision of 0.99, a recall of 1.00, and an F1 score of 0.99, with a latency time of 34.02 μs, which is 71.76% times faster than the original model.
Numerical Modelling of NACA 0015 Airfoil Under Erosion Condition Billad, Rayhan Fariansyah; Julian, James; Wahyuni, Fitri; Iskandar, Waridho
Jurnal Rekayasa Mesin Vol. 19 No. 2 (2024): Volume 19, Nomor 2, Agustus 2024
Publisher : Mechanical Engineering Department - Semarang State Polytechnic

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32497/jrm.v19i2.4992

Abstract

Airfoils that experience erosion with varying Reynolds numbers were studied using numerical methods to determine the effect on the performance of the NACA 0015 airfoil. A Computational Fluid Dynamics (CFD) approach has been used to this research. Reynolds Averaged Navier-Stokes (RANS) was used as the governing equation used in this research. The turbulence model used in this research was k-epsilon model. The Reynolds numbers used are 1.6 × 10⁶, 2 × 10⁶, and 2.5 × 10⁶. This research proves that erosion can reduce the Cl value and increase the Cd value on the NACA 0015 airfoil. Increasing the Reynolds number can also reduce the average Cl value and increase the average Cd value. The decrease in the average value of Cl is 6.561%, 9.392%, and 9.803%, respectively, at Reynolds numbers 1.6 × 10⁶, 2 × 10⁶, and 2.5 × 10⁶. Then, the average Cd value increase is 1.120%, 1.301%, and 1.396%, respectively, at Reynolds numbers 1.6 × 10⁶, 2 × 10⁶, and 2.5 × 10⁶. The contour visualization shows that the airfoil erosion has a pressure contour that increases in the upper chamber and decreases in the lower chamber. This phenomenon also occurs as the Reynolds number increases so that it can reduce the lifting force of the NACA 0015 airfoil. The flow velocity and streamlined contours also show greater circulating flow on the erosion airfoil, which can accelerate the 1 ° AoA stall on the erosion airfoil. The circulating flow also becomes larger as the Reynolds number of the airfoil increases.
The Influence of Fillet Step on Backward-Facing Step Flow Characteristics James Julian; Rizki Aldi Anggara; Fitri Wahyuni
Infotekmesin Vol 14 No 2 (2023): Infotekmesin: Juli, 2023
Publisher : P3M Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35970/infotekmesin.v14i2.1919

Abstract

Backward-facing step (BFS) is a model that provides several applicative features in engineering. The complex phenomena of BFS flow have a crucial impact on any application. Therefore, this study comprehensively investigates the flow characteristics of BFS with various step shapes. The backward-facing step (F-BFS) fillets were tested at intervals of Reynolds number 50 smaller than Re smaller than 400 using the CFD approach. Based on the computational results, it was found that flow separation is a fundamental phenomenon in BFS flow. Due to sudden expansion, Flow separation forms a recirculation area which continues to increase almost linearly with an increase in the Reynolds number. The recirculation area contains unstable rotating vortexes, which can impact the flow efficiency of BFS. Using a different step shape proves that F-BFS can minimize the recirculation area to increase the efficiency of the BFS flow.
Awareness Metode Pembelajaran Pasca Pandemi Covid-19 di SMKN 12 Jakarta Ferdyanto, Ferdyanto; Marbawi, Idris; Jannah, Miftahul; Patrick, Juan; Oktavia, Nana Triana; Firdaus, Talitha Fatiha; Julian, James; Tua, Lomo Mula
Jurnal Kreativitas Pengabdian Kepada Masyarakat (PKM) Vol 8, No 2 (2025): Volume 8 No 2 (2025)
Publisher : Universitas Malahayati Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33024/jkpm.v8i2.17486

Abstract

ABSTRAK Semua kegiatan mulai terganggu akibat pandemi Covid-19 yang sedang berlangsung, terutama di sektor pendidikan. Pelayanan masyarakat ini kemudian diharapkan dapat menganalisis tingkat pemahaman guru terhadap beberapa metode pembelajaran yang diterapkan berdasarkan perspektif guru SMKN 12 JAKARTA sebelum dan setelah berbagi pengetahuan. Dalam kegiatan ini, metode yang digunakan adalah kualitatif, dengan implementasi teknis adalah survei SMKN 12 JAKARTA yang dihadiri oleh 40 guru. Kegiatan dimulai dengan distribusi pre-test kepada para guru, dilanjutkan dengan berbagi pengetahuan dan diskusi tanyajawab. Kemudian diakhiri dengan distribusi kuesioner (post-test). Data dalam kuesioner kemudian diproses menggunakan uji skala Likert, yang mendapatkan hasil yang berbeda untuk setiap pertanyaan. Dengan demikian, kesimpulan yang diperoleh adalah para guru sudah memahami dasar-dasar metode pembelajaran, sinkronus dan asinkronus. Selanjutnya, di masa depan, mereka dapat mampu menjalankan metode pembelajaran secara mandiri. Kata Kunci: Asinkronus, Kuesioner, Metode Pembelajaran, Pasca Covid-19, Sinkronus ABSTRACT All activities began to be disrupted due to the ongoing Covid-19 pandemic, especially in the education sector. This community service is later expected to be able to analyze the level of teacher understanding of several learning methods that are applied based on the perspective of the SMKN 12 JAKARTA teacher before and after sharing knowledge. In this activity, the method used was qualitative, with the technical implementation being the SMKN 12 JAKARTA survey which 40 teachers attended. The activity began with distributing pre-tests to the teachers, followed by knowledge sharing and question-and-answer discussions, and then ended with distributing questionnaires (post-test). The data in the questionnaire was then processed using the Likert scale test, in which different results were found for each question. Thus the conclusions obtained by the teachers already understand the basics of learning methods, synchronous and asynchronous. Furthermore, it will be able to run the learning method independently in the future. Keywords: Asynchronous, Learning Method, Post Covid-19, Questionnaire, Synchronous
Investigation of Flap Dimensional Parameters to Improve Hydrodynamic Performance of Oscillating Wave Surge Converter Device Anggara, Rizki Aldi; Julian, James; Wahyuni, Fitri; Purba, Riki Hendra; Toding Bunga, Nely
Jurnal Asiimetrik: Jurnal Ilmiah Rekayasa & Inovasi Volume 7 Number 1 (2025)
Publisher : Fakultas Teknik Universitas Pancasila

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35814/asiimetrik.v7i1.7911

Abstract

Renewable energy transition is a strategic step in overcoming environmental damage due to fossil fuel exploitation. Ocean wave energy comes with its popularity, considering its advantages in supplying energy continuously and having high energy density. Therefore, technology that can extract other wave energy effectively and efficiently is needed. This study focuses on identification flap geometry to improve the oscillating wave surge converter (OWSC) hydrodynamic performance. Through a numerical approach, the Boundary Element Method (BEM) is applied in three-dimensional flap modeling to accommodate testing the characteristics and performance of the OWSC device. This study identified five different samples: geometry 1, geometry 2, geometry 3, geometry 4, and geometry 5. The results show that the second geometry variation is the most optimal flap dimension parameter. The best proportion is found in the dimensional characteristics parallel to the elevation of the ocean waves to maximize the output torque. Overall, the second geometry performs satisfactorily with an average maximum power achievement of 41.52 Watts at a wave period of T = 1.5s. In addition, the OWSC device with this variation can work at an expansive wave period interval with a maximum CWR efficiency achievement of up to 52.14%.
The Effect of Hydrostatic Pressure on the Performance of Oscillating Wave Surge Converter Prabowo, Anton Dwi; Julian, James; Wahyuni, Fitri; Purba, Riki Hendra; Toding Bunga, Nely
Jurnal Asiimetrik: Jurnal Ilmiah Rekayasa & Inovasi Volume 7 Number 1 (2025)
Publisher : Fakultas Teknik Universitas Pancasila

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35814/asiimetrik.v7i1.7912

Abstract

The latest energy demand increasingly drives innovation in ocean wave energy technology, including the Oscillating Wave Surge Converter (OWSC). This consider analyzes the impact of water profundity varieties on the execution of OWSCs put on the seabed. The study was conducted numerically using the Boundary Element Method by testing four variations of air depth at wave periods between 1.2 and 2.8 seconds and wave amplitudes of 0.1 meters. The results show that the optimal depth, equivalent to the flap height (D2), produces the highest maximum displacement due to the balance between hydrostatic pressure and wave energy the flap receives. Conversely, depths that are too shallow (D1) or too deep (D4) result in smaller displacements due to the instability of the movement in shallow air and the attenuation of wave energy in deep air. In addition, more extended wave periods tend to decrease the changing cycle frequency but increase the symmetry of the flap movement at a certain depth.
Utilization of Single and Double Orifice Plates in Pipe Inner Flow Structure by Computational Method Naufal, Ridwan Daris; Julian, James; Wahyuni, Fitri; Purba, Riki Hendra; Toding Bunga, Nely
Jurnal Asiimetrik: Jurnal Ilmiah Rekayasa & Inovasi Volume 7 Number 1 (2025)
Publisher : Fakultas Teknik Universitas Pancasila

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35814/asiimetrik.v7i1.7913

Abstract

The orifice plate is a device that disrupts the flow in the pipe. The disturbed flow results in the formation of flow structures. The flow structure formed can be utilized for several applications such as multi-fluid mixing and microbubble generator. Using orifice plates to utilize the flow structure results in more significant pressure loss. This study aims to identify the characteristics of the flow structure generated by single and double orifice plates with 1D and 2D spacing at various Reynolds numbers, namely Re = 1×104, 5×104, 1×105, and 5×105, as a basis for application in these various applications. The results show that single and double orifice plates can produce flow structure phenomena such as recirculation and vortex regions. The recirculation area is formed smaller in the double orifice plate due to the flow that is separated faster to converge back to the pipe wall but broader so that the flow of the orifice plate is narrower. Increasing the applied Reynold's number causes the separated flow to reconnect to the pipe wall faster, resulting in a smaller recirculation area. Double orifice plates are more suitable for applications that require a certain degree of mixing or pressure distribution, but with a consequent more significant pressure loss. Meanwhile, single plates can be used for simple needs with little pressure loss.
The Analysis of Banana Slices Machine Frame Using Computational Method Akmal, Reza Najmi; Julian, James; Wahyuni, Fitri; Purba, Riki Hendra; Toding Bunga, Nely
Jurnal Asiimetrik: Jurnal Ilmiah Rekayasa & Inovasi Volume 7 Number 1 (2025)
Publisher : Fakultas Teknik Universitas Pancasila

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35814/asiimetrik.v7i1.7914

Abstract

The culinary industry, especially banana chip processing, dramatically supports the economy of micro and small enterprises (MSMEs) in Indonesia. However, the traditional process is time-consuming, especially at the cutting stage. The banana-slicing machine is designed to speed up this process with consistent and efficient cuts. This study analyzes the performance of the banana-slicing machine frame by testing variations in loading (20 N to 200 N) and frame materials, namely Low Alloy Steel, Structural Steel, Stainless Steel, Aluminum Alloy, and Cast Iron, to determine the optimal material. The results showed that Low Alloy Steel is the best material because it has the lowest total deformation, equivalent stress, and strain energy, reflecting high stiffness and load efficiency. With an elastic modulus of 212.5 GPa and an economical price ($1.3–1.5/kg), this material offers the best balance in terms of technical and economics. Structural steel also performed well but was slightly lower than low alloy steel. In contrast, Aluminum Alloy has the highest deformation and strain energy, making it less suitable for this application. Overall, Low Alloy Steel is an ideal choice to improve the efficiency and reliability of the banana-slicing machine.
Co-Authors Achmad Zuchriadi Ade Fikri Fauzi Adi Winarta, Adi Akmal, Reza Najmi Aldi Anggara, Rizki Anggara, Rizki Aldi Annastya Bagas Dewantara Anton Prabowo Armansyah Armansyah Armansyah Armansyah Armansyah Bagas Dewantara, Annastya Billad, Rayhan Fariansyah Budiarso Budiarso, Budiarso Bunga, Nely Toding Demo Putra Demo Putra Desta Sandya Prasvita Dewantara, Annastya Bagas Dwi Yulia Handayani Elvi Armadani Ermadani, Elvi Faiz Daffa Ulhaq Farha, Auditya Fauzi, Ade Fikri Ferdyanto Ferdyanto, Ferdyanto Firdaus, Talitha Fatiha Fitri Wahyuni Fitri Wahyuni Fitri Wahyuni Fitri Wahyuni Gunasti, Nabilah Dwi Hadinata, Tri Hapidzha, Putty Harinaldi . I Wayan, Marlon Managi Idris Marbawi Iskandar, Waridho Junaedi, Thomas Juri Saedon Kasih Prihantoro Lomo Mula Tua Lumbantoruan, Regina Lumbantoruan, Regina Natalindah Madhudhu, Fathin Mahdhudhu, Fathin Muhammad Marbawi, Idris Miftahul Jannah Mirza Fauzan Lukiano Mufti Ahmad Fadilah Nandy Putra Naufal, Ridwan Daris Nisa, Rasya Aulia Nathania Nisa, Raysa Oktavia, Nana Triana Parker Stefan, Parker Patrick, Juan Prabowo, Anton Dwi Prakoso, Lukman Yudho Prasetyo, Eko Andi Purba, Riki Purba, Riki Hendra Putty Fauthyda Zahra Hapidzha Ramadhani, Rifqi Reda Rizal Revan Difitro, Revan Ridwan Daris Naufal Rifqi Ramadhani Rizki Aldi Anggara Rizki Aldi Anggara Rizki Anggara, Rizki Rudy Sutanto Saphira Anggraita Siswanto Sari, Rena Satria, Muhammad Fari Sedeq, Khalees Toding Bunga, Nely Tri Hadinata Tua, Lomo Mula Tulus Hidayat Yusanto Ulfa Hanifah Nurhaliza Ulhaq, Faiz Daffa Waridho Iskandar Waridho Iskandar Wijaya, Anggie Topan Yuliana, Sekar Zackharia Rialmi