Claim Missing Document
Check
Articles

Found 6 Documents
Search

Rancang Bangun Alat Pengepress Ban Elektrik untuk Merekatkan Ban Secara Otomatis Flora, Musthafa Adam; Madyono, Madyono; Iman, Budi Nur
INOVTEK - Seri Elektro Vol 3, No 2 (2021): INOVTEK Seri Elektro
Publisher : Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/ise.v3i2.2022

Abstract

The tire patch tools that we often encounter on the side of the road mostly use traditional tire filling tools with the manual press method and heating on an iron plate. And use spiritus that is burned in the furnace to glue the patch. The process of patching tires takes a long time and sometimes the patcher has to make sure, whether the patch is glued or not. The problem is when opening the patch too quickly results in the patch not being completely glued. Likewise, when patching for too long will damage the tire surface. From this problem came the idea to make a tire patch tool with a display to find out the temperature when the tire patch tool works and also the length of time for the tire patch so that the tire patch automatically stops. This tool will be implemented on the surrounding tire patch. This study aims to determine the optimal temperature for tire filling to produce good fillings in a short time when compared to the usual tire filling time. In this research, we use a thermocouple sensor, Arduino Pro mini, organic light-emitting diode (oled), and a dc motor. The results of the filling with the specified temperature and time variations obtained good and bad results. The optimal temperature for tire patching in this test is at 70 ÌŠ C the temperature on the heating plate, with perfect patching results for 1 minute 50 seconds. The heat transfer rate on the plate is 37,763 watts and the heat transfer rate on the tires is 0.45 watts.
Rancang bangun bobot kartesian tiga axis untuk penyiraman tanaman yang akurat dan efisien Tamami, Niam; Hermawan, Hendhi; Hanafi, Nofria; Madyono, Madyono; Perdana, Galang; Ramadhan, Farhan
JURNAL ELTEK Vol. 20 No. 2 (2022): Oktober 2022
Publisher : Politeknik Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/eltek.v20i2.351

Abstract

Untuk menunjang lahan pertanian yang subur, diperlukan proses penyiraman agar kadar air dalam tanah tetap terjaga. Kegiatan penyiraman yang dilakukan secara manual membutuhkan banyak energi. Selain itu kadar air yang diberikan dengan penyiraman manual tidak dapat terukur secara akurat. Dalam makalah ini, kami mengusulkan penyiraman otomatis dengan robot kartesian tiga aksis untuk lahan dengan ukuran 3 meter x 1.5 meter dengan 171 titik tanam. Kontrol penyiraman berbasis fuzzy agar kadar air yang diberikan bisa akurat. Sebelum penyiraman, rata-rata kelembapan tanah pada lahan tersebut adalah 45.28% dengan nilai minimal 40%, nilai maksimal 50%. Target kelembapan tanah untuk setiap titik adalah 60%. Robot dapat menyiram seluruh titik tanam tanpa campur tangan manusia. Nilai kadar air rata-rata setelah penyiraman adalah 62.10%, dengan nilai minimal 60%, nilai maksimal 65%. Selain itu, juga telah dibandingkan mekanisme penyiraman dengan metode fuzzy dengan metode on-off, metode fuzzy mampu menghasilkan penyiraman yang lebih akurat dengan tingkat kesalahan rata-rata 2.10%, sedangkan metode on-off memiliki tingkat kesalahan rata-rata 5.32% terhadap target nilai kelembapan tanah. Metode fuzzy juga lebih efisien waktu dalam penyiraman yaitu 7 detik hingga 8 detik, sedangkan metode onoff membutuhkan waktu penyiraman 10 detik hingga 15 detik.   ABSTRACT To support fertile agricultural land, a watering process is needed so that the water content in the soil is maintained. Watering activities carried out manually require a lot of energy. In addition, the water content given by manual watering cannot be measured accurately. In this paper, we propose automatic watering with a three-axis Cartesian robot for land with a size of 3 meters x 1.5 meters with 171 planting points. Fuzzy based watering control so that the water content given can be accurate. Before watering, the average soil moisture on the land was 45.28% with a minimum value of 40%, a maximum value of 50%. The target soil moisture for each point is 60%. The robot can water the entire planting point without human intervention. The average water content value of watering is 62.10%, with a minimum value of 60%, a maximum value of 65%. In addition, also compared with the application error with the fuzzy method with the on-offmethod, the fuzzy method is able to produce more accurate watering with an average error rate of 2.10%, while the on-off method has an average error of 5.32% against the soil moisture target. The fuzzy method is also more time efficient in watering, which is 7 seconds to 8 seconds, while the on-off method requires a watering time of 10 seconds to 15 seconds.
Detection of Tuberculosis Disease in Lung X-ray Images Using the DenseNet121 Method Madyono, Madyono; Nabilah, Anisah
International Journal of Engineering, Science and Information Technology Vol 5, No 2 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i2.853

Abstract

Tuberculosis (TB) is a lung infection caused by Mycobacterium tuberculosis and can be detected through chest X-ray imaging. In this study, tuberculosis disease detection was carried out using the DenseNet121 method, a deep-learning architecture proven effective in medical image classification tasks. This study used a dataset of 4,200 lung X-ray images classified as positive or negative for TB. The DenseNet121 model was trained with this data to identify patterns in the X-ray images indicating tuberculosis infection. The results of the model evaluation showed high performance with a precision value of 0.91, a recall of 0.90, and an f1-score of 0.89. In addition, the model achieved an overall accuracy of 90.4%. The results of this study indicate that the DenseNet121 method can be a reliable tool in detecting tuberculosis from chest X-ray images so that it can assist medical personnel in the diagnosis process more quickly and accurately.
Implementasi Media Informasi Berbasis Running Text untuk Meningkatkan Efisiensi dan Efektivitas Penyampaian Informasi di Kelurahan Keputih Tamami, Ni'am; Cipta Ramadhan , Ibnu; Alfathdyanto, Khairurizal; Madyono, Madyono; Hermawan, Hendhi; Megawati Rosalinda, Hanny; Waya Rahmaning Gusti, Agrippina; Trisniani, Widita
J-Dinamika : Jurnal Pengabdian Masyarakat Vol 10 No 2 (2025): Agustus
Publisher : Politeknik Negeri Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Pengabdian Kepada Masyarakat ini bertujuan untuk mengembangkan dan mengimplementasikan media informasi berbasis running text di Kelurahan Keputih, yang dirancang untuk meningkatkan efisiensi penyampaian informasi kepada masyarakat. Kelurahan Keputih sebelumnya mengandalkan banner sebagai media penyampaian informasi yang kurang fleksibel dan memakan waktu dalam proses pembaruan. Alat running text yang dikembangkan mempermudah pembaruan informasi secara cepat dan efisien. Untuk mengevaluasi efektivitas alat, dilakukan survei kepuasan dengan kuisioner kepada 10 responden yang terdiri dari staf kelurahan dan masyarakat. Rata-rata keseluruhan dari semua pertanyaan dalam skala 1-10 adalah 8,56. Hasil survei menunjukkan bahwa alat ini dinilai sangat menarik, mudah digunakan, dan mampu mempercepat pembuatan konten pengumuman. Hasil ini menunjukkan bahwa alat running text berhasil memenuhi kebutuhan Kelurahan Keputih dalam menyampaikan informasi publik secara efisien.
An Adaptive Automatic Braking System for Enhanced Road Safety : English Pratama, Wildan; Cahya Happyanto, Dedid; Wijayanto, Ardik; Alrijadjis, Alrijadjis; Madyono, Madyono
Emitor: Jurnal Teknik Elektro Vol 25, No 3: November 2025
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/emitor.v25i3.11378

Abstract

The fuzzy logic-based automatic braking system was developed to improve driving safety by reducing reliance on the driver's attention. The system integrates a LiDAR sensor for distance, a magnetic speed sensor for speed, and an ESP32 microcontroller as the main control. The advantage of this system lies in its ability to process data from various parameters adaptively and quickly using the rules of fuzzy logic. Communication between modules is supported by the CANBUS protocol to ensure fast and accurate data exchange. Tests show that the LiDAR proximity sensor has high accuracy with an average error of less than 1%. The speed sensor shows a consistent relationship between the frequency of the inverter and the speed of the car, with an average error of 7.1% on the deceleration. The fuzzy system successfully replicates MATLAB output with relatively few errors, and a more stable Duty Cycle setting than without fuzzy. This proves that the system is adaptive and responsive in a wide range of operational conditions.
Human Bone Age Estimation of Carpal Bone X-Ray Using Residual Network with Batch Normalization Classification Nabilah, Anisah; Sigit, Riyanto; Fariza, Arna; Madyono, Madyono
JOIV : International Journal on Informatics Visualization Vol 7, No 1 (2023)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30630/joiv.7.1.1024

Abstract

Bone age is an index used by pediatric radiology and endocrinology departments worldwide to define skeletal maturity for medical and non-medical purposes. In general, the clinical method for bone age assessment (BAA) is based on examining the visual ossification of individual bones in the left hand and then comparing it with a standard radiographic atlas of the hand. However, this method is highly dependent on the experience and conditions of the forensic expert. This paper proposes a new approach to age estimation of human bone based on the carpal bones in the hand and using a residual network architecture. The classification layer was modified with batch normalization to optimize the training process. Before carrying out the training process, we performed an image augmentation technique to make the dataset more varied. The following augmentation techniques were used: resizing; random affine transformation; horizontal flipping; adjusting brightness, contrast, saturation, and hue; and image inversion. The output is the classification of bone age in the range of 1 to 19 years. The results obtained when using a VGG16 model were an MAE value of 5.19 and an R2 value of 0.56 while using the newly developed ResNeXt50(32x4d) model produced an MAE value of 4.75 and an R2 value of 0.63. The research results indicate that the proposed modification of the residual training model improved classification compared to using the VGG16 model, as indicated by an MAE value of 4.75 and an R2 value of 0.63.